file-organizer

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an indirect prompt injection vulnerability surface because it processes untrusted user files and contents.
  • Ingestion points: Untrusted data enters the agent context through file metadata, names, and file contents when analyzing user directories such as Downloads or Documents (SKILL.md).
  • Boundary markers: Absent; there are no instructions or delimiters defined to prevent the agent from executing instructions that might be embedded within the names or contents of the files being organized.
  • Capability inventory: The skill uses filesystem capabilities including creating directories (mkdir) and moving/renaming files (mv) across the user's local system (SKILL.md).
  • Sanitization: Absent; filenames and file contents are interpolated directly into the organization workflow without prior validation or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:22 PM
Security Audit — agent-trust-hub — file-organizer