bootstrapping-docs
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to run a Python script at $CLAUDE_PLUGIN_ROOT/engine/doc-lifecycle.py to manage the documentation registry.
- [PROMPT_INJECTION]: The skill requires the agent to explore the repository, creating an indirect prompt injection surface where malicious repository content could influence the agent. 1. Ingestion points: build scripts, orchestration files, entry points, and environment configuration surfaces (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: File system writes and local command execution. 4. Sanitization: Absent; the skill relies on the agent's internal reasoning during document creation.
Audit Metadata