thrunt-do — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited thrunt-do (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> Analyze freeform natural language input and dispatch to the most appropriate hunt or THRUNT command.
Acts as a smart dispatcher — never does the work itself. Matches intent to the best command using routing rules, confirms the match, then hands off.
Use when you know what you want but don't know which /thrunt:* or /hunt:* command to run. </objective>
<execution_context> @.github/thrunt-god/workflows/do.md @.github/thrunt-god/references/ui-brand.md </execution_context>
<context> $ARGUMENTS </context>
<process> Execute the do workflow from @.github/thrunt-god/workflows/do.md end-to-end. Route user intent to the best hunt or THRUNT command and invoke it. </process>
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.