thrunt-debug — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited thrunt-debug (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> Debug issues using scientific method with subagent isolation.
Orchestrator role: Gather symptoms, spawn thrunt-incident-debugger agent, handle checkpoints, spawn continuations.
Why subagent: Investigation burns context fast (reading files, forming hypotheses, testing). Fresh 200k context per investigation. Main context stays lean for user interaction. </objective>
<available_agent_types> Valid THRUNT subagent types (use exact names — do not fall back to 'general-purpose'):
</available_agent_types>
<context> User's issue: $ARGUMENTS
Check for active sessions:
ls .planning/debug/*.md 2>/dev/null | grep -v resolved | head -5</context>
<process>
INIT=$(node ".github/thrunt-god/bin/thrunt-tools.cjs" state load)
if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fiExtract commit_docs from init JSON. Resolve debugger model:
debugger_model=$(node ".github/thrunt-god/bin/thrunt-tools.cjs" resolve-model thrunt-incident-debugger --raw)If active sessions exist AND no $ARGUMENTS:
If $ARGUMENTS provided OR user describes new issue:
Use AskUserQuestion for each:
After all gathered, confirm ready to investigate.
Fill prompt and spawn:
<objective>
Investigate issue: {slug}
**Summary:** {trigger}
</objective>
<symptoms>
expected: {expected}
actual: {actual}
errors: {errors}
reproduction: {reproduction}
timeline: {timeline}
</symptoms>
<mode>
symptoms_prefilled: true
goal: find_and_fix
</mode>
<debug_file>
Create: .planning/debug/{slug}.md
</debug_file>Task(
prompt=filled_prompt,
subagent_type="thrunt-incident-debugger",
model="{debugger_model}",
description="Debug {slug}"
)If `## ROOT CAUSE FOUND`:
If `## CHECKPOINT REACHED`:
human-verify:If `## INVESTIGATION INCONCLUSIVE`:
When user responds to checkpoint, spawn fresh agent:
<objective>
Continue debugging {slug}. Evidence is in the debug file.
</objective>
<prior_state>
<files_to_read>
- .planning/debug/{slug}.md (Debug session state)
</files_to_read>
</prior_state>
<checkpoint_response>
**Type:** {checkpoint_type}
**Response:** {user_response}
</checkpoint_response>
<mode>
goal: find_and_fix
</mode>Task(
prompt=continuation_prompt,
subagent_type="thrunt-incident-debugger",
model="{debugger_model}",
description="Continue debug {slug}"
)</process>
<success_criteria>
</success_criteria>
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.