hunt-validate-findings — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited hunt-validate-findings (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 4 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 4 flagged
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<objective> Validate the current hunt's findings.
FINDINGS.md and EVIDENCE_REVIEW.md remain the source of truth for validation.
Creates or updates:
.planning/FINDINGS.md.planning/EVIDENCE_REVIEW.md.planning/STATE.mdAfter this command: Run /hunt-publish. </objective>
<execution_context> @.github/thrunt-god/workflows/hunt-validate-findings.md @.github/thrunt-god/templates/findings.md @.github/thrunt-god/templates/evidence-review.md </execution_context>
<process> Execute the validation workflow from @.github/thrunt-god/workflows/hunt-validate-findings.md. Mark each hypothesis as supported, disproven, or inconclusive. Call out evidence gaps explicitly. </process>
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.