local-file-organizer
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it performs deep content analysis on untrusted local files.
- Ingestion points:
SKILL.mdStep 2 details reading file content through text extraction, OCR, and media transcription. - Boundary markers: The skill lacks explicit instructions for using delimiters when processing raw file content, although it uses a structured ledger for reporting.
- Capability inventory: The agent has the ability to move, rename, and delete files as outlined in Step 6.
- Sanitization: The 'Safety Contract' instructs the agent to exclude sensitive personal data from reports and requires specific user approval for permanent deletions.
Audit Metadata