AgentWatchr

Kiro CLI

Evidence quality, not reputation. Missing data: N/A.

Kiro CLI โ€” source profile from acp_registry. First observed: 2026-11-02T18:17:18.885821+00:00; last observed: 2026-11-02T18:17:18.885821+00:00. Source-declared data; task execution has not been verified.

changes endpoints evidence history infrastructure relationships

Overall: N/A โ€” INSUFFICIENT_EVIDENCE

Coverage: 3/6 (50.0%)

Task Performance: N/A โ€” NOT TESTED

identity
value
N/A
status
SOURCE_OBSERVED
coverage
True
confidence
low
why this score
Captured source identity; ownership and source claims are not independently verified.
reason codes
  • SOURCE_OBSERVED
  • OBSERVED
evidence refs
  • acp:kiro:sha256:52a66324ea382ecf5a5672f4ea263496ed2c30e2ceb3683779d4aaf06b261b73:run:ff2cd554f510445aa2e6b094baf7b3d8
observation count
1
methodology version
evidence-score/0.2.1
assessment state
OBSERVED
applicability
APPLICABLE_OR_UNKNOWN
na reason
N/A
last observed at
2026-11-02T18:17:18.885821+00:00
freshness days
0.2091
confidence basis
calibrated probability
N/A
independent corroboration
N/A
meaning
Legacy confidence labels describe source attribution only; not probability.
distinct payloads
1
source labels
  • acp_registry
measurement
numerator
1
denominator
1
value
1.0
unit
valid source observation references / referenced observations
runtime
value
N/A
status
N/A
coverage
False
confidence
insufficient
why this score
HTTP responses including 405 and protocol recognition do not demonstrate task success.
reason codes
  • N/A
  • NOT_APPLICABLE
evidence refs
N/A
observation count
0
methodology version
evidence-score/0.2.1
assessment state
NOT_APPLICABLE
applicability
PUBLIC_HTTP_NOT_REQUIRED_BY_ACP_CLASS
na reason
NOT_APPLICABLE
last observed at
N/A
freshness days
N/A
confidence basis
calibrated probability
N/A
independent corroboration
N/A
meaning
Legacy confidence labels describe source attribution only; not probability.
distinct payloads
0
source labels
N/A
measurement
numerator
0
denominator
0
value
N/A
unit
HTTP responses / distinct dated attempts; NOT task success
historical
value
N/A
status
N/A
coverage
False
confidence
insufficient
why this score
Distinct observation times measure history, not independent corroboration.
reason codes
  • N/A
  • NO_DATA
evidence refs
N/A
observation count
1
methodology version
evidence-score/0.2.1
assessment state
NO_DATA
applicability
APPLICABLE_OR_UNKNOWN
na reason
NO_DATA
last observed at
N/A
freshness days
N/A
confidence basis
calibrated probability
N/A
independent corroboration
N/A
meaning
Legacy confidence labels describe source attribution only; not probability.
distinct payloads
0
source labels
N/A
measurement
distinct observation times
1
distinct payloads
1
independent confirmations
N/A
infrastructure
value
N/A
status
DECLARED_INFRASTRUCTURE
coverage
True
confidence
low
why this score
Source-declared infrastructure. Shared infrastructure has no penalty.
reason codes
  • DECLARED_INFRASTRUCTURE
  • OBSERVED
evidence refs
  • acp:kiro:sha256:52a66324ea382ecf5a5672f4ea263496ed2c30e2ceb3683779d4aaf06b261b73:run:ff2cd554f510445aa2e6b094baf7b3d8
observation count
1
methodology version
evidence-score/0.2.1
assessment state
OBSERVED
applicability
APPLICABLE_OR_UNKNOWN
na reason
N/A
last observed at
2026-11-02T18:17:18.885821+00:00
freshness days
0.2091
confidence basis
calibrated probability
N/A
independent corroboration
N/A
meaning
Legacy confidence labels describe source attribution only; not probability.
distinct payloads
1
source labels
  • acp_registry
measurement
numerator
1
denominator
1
value
1.0
unit
attributed declarations / declarations
consistency relationships
value
N/A
status
SOURCE_RELATIONSHIPS
coverage
True
confidence
low
why this score
Recorded relationships are not verified consistency or confirmed duplicates.
reason codes
  • SOURCE_RELATIONSHIPS
  • OBSERVED
evidence refs
  • acp:kiro:sha256:52a66324ea382ecf5a5672f4ea263496ed2c30e2ceb3683779d4aaf06b261b73:run:ff2cd554f510445aa2e6b094baf7b3d8
observation count
3
methodology version
evidence-score/0.2.1
assessment state
OBSERVED
applicability
APPLICABLE_OR_UNKNOWN
na reason
N/A
last observed at
2026-11-02T18:17:18.885821+00:00
freshness days
0.2091
confidence basis
calibrated probability
N/A
independent corroboration
N/A
meaning
Legacy confidence labels describe source attribution only; not probability.
distinct payloads
1
source labels
  • acp_registry
measurement
numerator
3
denominator
3
value
1.0
unit
attributed relations / declared relations; NOT confirmed consistency
conflicting runtime observation groups
0
task performance
value
N/A
status
N/A
coverage
False
confidence
insufficient
why this score
No accepted task-evaluation evidence schema or real task tests in this dataset.
reason codes
  • N/A
  • NOT_TESTED
evidence refs
N/A
observation count
N/A
methodology version
evidence-score/0.2.1
assessment state
NOT_TESTED
applicability
APPLICABLE_OR_UNKNOWN
na reason
NOT_TESTED
last observed at
N/A
freshness days
N/A
confidence basis
calibrated probability
N/A
independent corroboration
N/A
meaning
Legacy confidence labels describe source attribution only; not probability.
distinct payloads
0
source labels
N/A
measurement
accepted tests
0
successes
N/A
denominator
0
value
N/A
Why this score?
{
  "methodology": "evidence-score/0.2.1",
  "methodology_version": "evidence-score/0.2.1",
  "as_of": "2026-11-02T23:18:27.298790+00:00",
  "evaluated_at": "2026-11-02T23:18:27.298790+00:00",
  "snapshot_id": "profile-input-sha256:2657528ded15fd464c543038fa250695676e3704eace6d07dbc0afd99458091d",
  "profile_type": "PACKAGED_ACP_AGENT",
  "overall_score": null,
  "status": "INSUFFICIENT_EVIDENCE",
  "evidence_score": null,
  "overall_status": "INSUFFICIENT_EVIDENCE",
  "dimensions": {
    "identity": {
      "value": null,
      "status": "SOURCE_OBSERVED",
      "coverage": true,
      "confidence": "low",
      "why_this_score": "Captured source identity; ownership and source claims are not independently verified.",
      "reason_codes": [
        "SOURCE_OBSERVED",
        "OBSERVED"
      ],
      "evidence_refs": [
        "acp:kiro:sha256:52a66324ea382ecf5a5672f4ea263496ed2c30e2ceb3683779d4aaf06b261b73:run:ff2cd554f510445aa2e6b094baf7b3d8"
      ],
      "observation_count": 1,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-11-02T18:17:18.885821+00:00",
      "freshness_days": 0.2091,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 1,
        "source_labels": [
          "acp_registry"
        ]
      },
      "measurement": {
        "numerator": 1,
        "denominator": 1,
        "value": 1.0,
        "unit": "valid source observation references / referenced observations"
      }
    },
    "runtime": {
      "value": null,
      "status": "N/A",
      "coverage": false,
      "confidence": "insufficient",
      "why_this_score": "HTTP responses including 405 and protocol recognition do not demonstrate task success.",
      "reason_codes": [
        "N/A",
        "NOT_APPLICABLE"
      ],
      "evidence_refs": [],
      "observation_count": 0,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "NOT_APPLICABLE",
      "applicability": "PUBLIC_HTTP_NOT_REQUIRED_BY_ACP_CLASS",
      "na_reason": "NOT_APPLICABLE",
      "last_observed_at": null,
      "freshness_days": null,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 0,
        "source_labels": []
      },
      "measurement": {
        "numerator": 0,
        "denominator": 0,
        "value": null,
        "unit": "HTTP responses / distinct dated attempts; NOT task success"
      }
    },
    "historical": {
      "value": null,
      "status": "N/A",
      "coverage": false,
      "confidence": "insufficient",
      "why_this_score": "Distinct observation times measure history, not independent corroboration.",
      "reason_codes": [
        "N/A",
        "NO_DATA"
      ],
      "evidence_refs": [],
      "observation_count": 1,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "NO_DATA",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": "NO_DATA",
      "last_observed_at": null,
      "freshness_days": null,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 0,
        "source_labels": []
      },
      "measurement": {
        "distinct_observation_times": 1,
        "distinct_payloads": 1,
        "independent_confirmations": null
      }
    },
    "infrastructure": {
      "value": null,
      "status": "DECLARED_INFRASTRUCTURE",
      "coverage": true,
      "confidence": "low",
      "why_this_score": "Source-declared infrastructure. Shared infrastructure has no penalty.",
      "reason_codes": [
        "DECLARED_INFRASTRUCTURE",
        "OBSERVED"
      ],
      "evidence_refs": [
        "acp:kiro:sha256:52a66324ea382ecf5a5672f4ea263496ed2c30e2ceb3683779d4aaf06b261b73:run:ff2cd554f510445aa2e6b094baf7b3d8"
      ],
      "observation_count": 1,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-11-02T18:17:18.885821+00:00",
      "freshness_days": 0.2091,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 1,
        "source_labels": [
          "acp_registry"
        ]
      },
      "measurement": {
        "numerator": 1,
        "denominator": 1,
        "value": 1.0,
        "unit": "attributed declarations / declarations"
      }
    },
    "consistency_relationships": {
      "value": null,
      "status": "SOURCE_RELATIONSHIPS",
      "coverage": true,
      "confidence": "low",
      "why_this_score": "Recorded relationships are not verified consistency or confirmed duplicates.",
      "reason_codes": [
        "SOURCE_RELATIONSHIPS",
        "OBSERVED"
      ],
      "evidence_refs": [
        "acp:kiro:sha256:52a66324ea382ecf5a5672f4ea263496ed2c30e2ceb3683779d4aaf06b261b73:run:ff2cd554f510445aa2e6b094baf7b3d8"
      ],
      "observation_count": 3,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "OBSERVED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": null,
      "last_observed_at": "2026-11-02T18:17:18.885821+00:00",
      "freshness_days": 0.2091,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 1,
        "source_labels": [
          "acp_registry"
        ]
      },
      "measurement": {
        "numerator": 3,
        "denominator": 3,
        "value": 1.0,
        "unit": "attributed relations / declared relations; NOT confirmed consistency"
      },
      "conflicting_runtime_observation_groups": 0
    },
    "task_performance": {
      "value": null,
      "status": "N/A",
      "coverage": false,
      "confidence": "insufficient",
      "why_this_score": "No accepted task-evaluation evidence schema or real task tests in this dataset.",
      "reason_codes": [
        "N/A",
        "NOT_TESTED"
      ],
      "evidence_refs": [],
      "observation_count": null,
      "methodology_version": "evidence-score/0.2.1",
      "assessment_state": "NOT_TESTED",
      "applicability": "APPLICABLE_OR_UNKNOWN",
      "na_reason": "NOT_TESTED",
      "last_observed_at": null,
      "freshness_days": null,
      "confidence_basis": {
        "calibrated_probability": null,
        "independent_corroboration": null,
        "meaning": "Legacy confidence labels describe source attribution only; not probability.",
        "distinct_payloads": 0,
        "source_labels": []
      },
      "measurement": {
        "accepted_tests": 0,
        "successes": null,
        "denominator": 0,
        "value": null
      }
    }
  },
  "coverage": 50.0,
  "coverage_facets": {
    "identity": true,
    "runtime": false,
    "historical": false,
    "infrastructure": true,
    "consistency_relationships": true,
    "task_performance": false
  },
  "coverage_denominator": 6,
  "coverage_numerator": 3,
  "coverage_exclusions": [],
  "coverage_basis": "Fixed six evidence areas; applicability never shrinks denominator.",
  "record_quality": {
    "numerator": 1,
    "denominator": 1,
    "value": 1.0,
    "unit": "valid attributed observation references / all referenced observations"
  },
  "verification_scope": {
    "http_attempts": 0,
    "http_responses": 0,
    "task_tests": 0
  },
  "freshness": {
    "source_last_observed_at": "2026-11-02T18:17:18.885821+00:00",
    "runtime_last_tested_at": null
  },
  "evidence_confidence": "low",
  "confidence": "low",
  "independent_corroboration": null,
  "runtime": null,
  "task_success": null,
  "reason_codes": [
    "NO_VALIDATED_COMPOSITE",
    "TASK_PERFORMANCE_NOT_TESTED",
    "MISSING_DATA_NOT_A_PENALTY",
    "CORRELATION_NOT_ABUSE",
    "SOURCE_CLAIMS_NOT_INDEPENDENTLY_VERIFIED",
    "INSUFFICIENT_EVIDENCE"
  ],
  "evidence_refs": [
    "acp:kiro:sha256:52a66324ea382ecf5a5672f4ea263496ed2c30e2ceb3683779d4aaf06b261b73:run:ff2cd554f510445aa2e6b094baf7b3d8"
  ],
  "why_this_score": "No composite: evidence axes have different meanings and no calibrated common scale. N/A is neither zero nor success.",
  "components": [],
  "freshness_days": 0.2091,
  "input_sha256": "202db357417ebe71c3099a4526b9b23851a6eddd1a4d40d50cb4f71b8e9724a6",
  "meaning": "Observed evidence coverage, not reputation, safety, recommendation or task ability."
}
Methodology v0.2
N/A