thrunt-quick — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited thrunt-quick (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> Execute small, ad-hoc tasks with THRUNT guarantees (atomic commits, STATE.md tracking).
Quick mode is the same system with a shorter path:
.planning/quick/ separate from planned phasesDefault: Skips research, discussion, plan-checker, and findings validation. Use when you know exactly what to do.
`--discuss` flag: Lightweight discussion phase before planning. Surfaces assumptions, clarifies gray areas, captures decisions in CONTEXT.md. Use when the task has ambiguity worth resolving upfront.
`--full` flag: Enables plan-checking (max 2 iterations) and post-execution findings validation. Use when you want quality guarantees without full milestone ceremony.
`--research` flag: Spawns a focused research agent before planning. Investigates implementation approaches, library options, and pitfalls for the task. Use when you're unsure of the best approach.
Flags are composable: --discuss --research --full gives discussion + research + plan-checking + findings validation. </objective>
<execution_context> @.github/thrunt-god/workflows/quick.md </execution_context>
<context> $ARGUMENTS
Context files are resolved inside the workflow (init quick) and delegated via <files_to_read> blocks. </context>
<process> Execute the quick workflow from @.github/thrunt-god/workflows/quick.md end-to-end. Preserve all workflow gates (validation, task description, planning, execution, state updates, commits). </process>
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.