thrunt-add-backlog — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited thrunt-add-backlog (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> Add a backlog item to the huntmap using 999.x numbering. Backlog items are unsequenced ideas that aren't ready for active planning — they live outside the normal phase sequence and accumulate context over time. </objective>
<process>
cat .planning/HUNTMAP.md NEXT=$(node ".github/thrunt-god/bin/thrunt-tools.cjs" phase next-decimal 999 --raw)If no 999.x phases exist, start at 999.1.
SLUG=$(node ".github/thrunt-god/bin/thrunt-tools.cjs" generate-slug "$ARGUMENTS")
mkdir -p ".planning/phases/${NEXT}-${SLUG}"
touch ".planning/phases/${NEXT}-${SLUG}/.gitkeep"## Backlog section. If the section doesn't exist, create it at the end: ## Backlog
### Phase {NEXT}: {description} (BACKLOG)
**Goal:** [Captured for future planning]
**Hypotheses:** TBD
**Plans:** 0 plans
Plans:
- [ ] TBD (promote with /thrunt-review-backlog when ready) node ".github/thrunt-god/bin/thrunt-tools.cjs" commit "docs: add backlog item ${NEXT} — ${ARGUMENTS}" --files .planning/HUNTMAP.md ".planning/phases/${NEXT}-${SLUG}/.gitkeep" ## 📋 Backlog Item Added
Phase {NEXT}: {description}
Directory: .planning/phases/{NEXT}-{slug}/
This item lives in the backlog parking lot.
Use /hunt-shape-hypothesis {NEXT} to explore it further.
Use /thrunt-review-backlog to promote items to active milestone.</process>
<notes>
Depends on: field — backlog items are unsequenced by definition</notes>
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.