meetings-cleanup

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local shell utilities (find, du, rm, mv) to analyze and manage files within the user's ~/vault/meetings/ and ~/.minutes/ directories. These operations are consistent with the stated purpose of storage management and cleanup.- [PROMPT_INJECTION]: The skill processes filenames from the local filesystem, which serves as a potential surface for indirect prompt injection if a filename contained malicious instructions.
  • Ingestion points: Local file system via find and du commands in SKILL.md.
  • Boundary markers: Absent from the command strings, though the skill body includes explicit instructions for the agent to confirm actions with the user.
  • Capability inventory: File system modification permissions including deletion (rm, find -delete) and movement (mv) across scripts.
  • Sanitization: Filenames are processed directly via shell utilities without specific validation or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 06:17 AM
Security Audit — agent-trust-hub — meetings-cleanup