hunt-map-environment — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited hunt-map-environment (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> Create or refresh the environment map for this hunt program or case.
Creates or updates:
.planning/environment/ENVIRONMENT.md.planning/MISSION.md.planning/HYPOTHESES.md.planning/STATE.mdUnknown tenants, tools, retention windows, access paths, and blind spots must remain TBD until the operator confirms them. Confirmed environment facts should replace existing TBD markers immediately; only unresolved fields should stay TBD.
After this command: Run /hunt-shape-hypothesis or /hunt-plan 1. </objective>
<execution_context> @.github/thrunt-god/workflows/hunt-map-environment.md @.github/thrunt-god/templates/environment-map.md </execution_context>
<process> Execute the environment-mapping workflow from @.github/thrunt-god/workflows/hunt-map-environment.md. Prefer concrete environment facts over generic best practices. Preserve existing analyst notes. Default behavior is to preserve confirmed facts and leave unknown values as TBD rather than populating simulated environment details. Replace TBD only where live workspace evidence or direct operator input confirms the fact. </process>
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.