estate-hygiene

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands including git, grep, mv, and wc to gather evidence and manage repository files. It specifically implements a 'retire pattern' that moves directories to a ~/trash/ location.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: Data is ingested from the file system, including repository names, git logs, and file contents via grep -rl. It also reads configuration data from ~/vault/missions.md.
  • Boundary markers: There are no boundary markers or instructions to isolate potentially malicious data found within the repositories being audited.
  • Capability inventory: The skill possesses shell execution capabilities (git, mv, grep) and file system write access for moving directories.
  • Sanitization: The skill lacks explicit sanitization or validation mechanisms for the data retrieved from repositories before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 01:02 AM
Security Audit — agent-trust-hub — estate-hygiene