compile-apm-package — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited compile-apm-package (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
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.
This skill generates merged context documents from APM primitives. This is primarily required for harnesses that consume a single authoritative file (like Gemini's GEMINI.md) rather than distributed skill directories.
AGENTS.md, etc.) are generated artifacts. NEVER edit them directly if a .apm/ source tree exists.install-apm-package.apm compile.apm compile to verify how fragments merge into the final doc.apm.yml existence.python scripts/validate_apm_package.py.apm compile [--target <slug>].apm compile for a Claude Code project (redundant work).GEMINI.md instead of the source .prompt.md.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.