folder-specific-claude-and-agents-md
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires reading all files in a target folder to generate documentation, creating a surface for indirect prompt injection if those files contain malicious instructions. However, this is necessary for the skill's core functionality. * Ingestion points: Local folder files (Step 2). * Boundary markers: None. * Capability inventory: File creation, symlink creation, and git commands. * Sanitization: None.
- [COMMAND_EXECUTION]: The skill uses a standard shell command (
ln -s) to create a symbolic link between documentation files.
Audit Metadata