verify-manual
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses git diff to analyze code changes and mkdir -p to manage documentation directories. These are standard operations for development automation within the local environment.
- [PROMPT_INJECTION]: The skill processes untrusted data from the local repository (via git diff) and interpolates it into the output without boundary markers or sanitization. This creates a surface for indirect prompt injection where malicious instructions embedded in code comments could affect the generated handbook.
- Ingestion points: Reads repository diffs using git diff in SKILL.md.
- Boundary markers: Absent; the skill does not use delimiters to isolate the diff content from its own instructions.
- Capability inventory: Local file system writes and command execution.
- Sanitization: Absent; the skill does not filter or escape content retrieved from the code analysis.
Audit Metadata