filesystem
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill provides tools for reading file contents, which creates an attack surface where data processed by the agent could contain instructions designed to influence its behavior.
- Ingestion points: read_file, list_directory (SKILL.md).
- Boundary markers: Absent in the skill definition.
- Capability inventory: write_file, save_file, apply_file_changes (SKILL.md).
- Sanitization: No sanitization or validation of file content is described.
Audit Metadata