thrunt-milestone-summary — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited thrunt-milestone-summary (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> Generate a structured milestone summary for team onboarding and project review. Reads completed milestone artifacts (HUNTMAP, HYPOTHESES, CONTEXT, SUMMARY, VERIFICATION files) and produces a human-friendly overview of what was built, how, and why.
Purpose: Enable new team members to understand a completed project by reading one document and asking follow-up questions. Output: MILESTONE_SUMMARY written to .planning/reports/, presented inline, optional interactive Q&A. </objective>
<execution_context> @.github/thrunt-god/workflows/milestone-summary.md </execution_context>
<context> Project files:
.planning/HUNTMAP.md.planning/MISSION.md.planning/STATE.md.planning/RETROSPECTIVE.md.planning/milestones/v{version}-HUNTMAP.md (if archived).planning/milestones/v{version}-HYPOTHESES.md (if archived).planning/phases/*-*/ (SUMMARY.md, FINDINGS.md, CONTEXT.md, RESEARCH.md)User input:
</context>
<process> Read and execute the milestone-summary workflow from @.github/thrunt-god/workflows/milestone-summary.md end-to-end. </process>
<success_criteria>
.planning/reports/MILESTONE_SUMMARY-v{version}.md</success_criteria>
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.