hunt-shape-hypothesis — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited hunt-shape-hypothesis (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> Refine the active signal into testable hunt hypotheses.
HYPOTHESES.md, SUCCESS_CRITERIA.md, and HUNTMAP.md remain the source of truth.
Updates:
.planning/HYPOTHESES.md.planning/SUCCESS_CRITERIA.md.planning/HUNTMAP.md.planning/STATE.mdAfter this command: Run /hunt-plan 1 or /hunt-run 1 if plans already exist. </objective>
<execution_context> @.github/thrunt-god/workflows/hunt-shape-hypothesis.md @.github/thrunt-god/templates/hypotheses.md @.github/thrunt-god/templates/success-criteria.md @.github/thrunt-god/templates/huntmap.md </execution_context>
<process> Execute the hypothesis-shaping workflow from @.github/thrunt-god/workflows/hunt-shape-hypothesis.md. Drive toward hypotheses that can be proven, disproven, or left explicitly inconclusive. </process>
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.