vault-cleanup-auditor

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the bash tool to run scripts for file system traversal and content analysis (using find, grep, stat, and wc) based on a path provided by the user.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface. Ingestion points: Filenames and content from the vault are read using find and grep in SKILL.md and SKILL-OC.md. Boundary markers: No specific delimiters are used to wrap or isolate the ingested file data from the agent's instructions. Capability inventory: The skill utilizes the bash tool to search the filesystem and write audit reports. Sanitization: The skill does not explicitly sanitize data retrieved from the vault (like filenames or grep results) before it is processed by the agent to generate the report summary.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 12:23 AM