Public Trust Report
Trust Agent publishes the score, findings, analyst narrative, and artefact fingerprint while keeping prompts, code, and protected configuration inside the secure review boundary.
Audit outcome
PASSED
Stage scores
S1 84 / S2 92 / S3 88
Artefact hash
4707b5985459b9e0344f0e0f029b95f81cce08c6655a414678400de4113899bd
Signed at
3/31/2026, 11:35:12 AM
Early Maths Mastery completed the Trust Agent automated review pipeline for skill listings. Stage 1 configuration integrity scored 84/100 and stage 2 behaviour testing scored 92/100. The companion security scan produced 73/100 with outcome PASSED. Overall trust score: 81/100. Primary analyst watchpoints: Skill outcomes are too vague, Skill tool manifest lacks structure, Skill fragment may override parent role judgment. This public narrative excludes prompts, code, and protected configuration while preserving the buyer-facing trust rationale.
Skill outcomes are too vague
vague-capabilities
Skill packs should publish at least three concrete delegation outcomes so buyers understand the attachment value.
Recommended action: Expand the skill outcomes list with concrete deliverables and specialist interventions.
Skill tool manifest lacks structure
manifest-mismatch
The skill does not clearly describe its delegation interface, data requirements, or tooling assumptions.
Recommended action: Add supported formats, delegation mode, and expected tool dependencies to the manifest.
Skill fragment may override parent role judgment
persona-drift
Badge state
SECURITY FAILED
Passed checks
29
Critical / high
0 / 1
Verification ID
scan_0e0be019f7f84311
Trust Agent publishes buyer-safe evidence only. If you are the creator and need full remediation details, use your creator dashboard or admin review access rather than the public report.
The skill speaks in unconditional terms that could dominate the parent role rather than acting as a bounded specialist helper.
Recommended action: Rewrite the skill fragment so it offers specialist support within the parent role's approval and escalation model.
Analyst follow-up summary
edge-case-fail
Analyst review highlighted follow-up watchpoints: Skill outcomes are too vague, Skill tool manifest lacks structure, Skill fragment may override parent role judgment.
Recommended action: Address the highlighted watchpoints in the next submitted version.
