housekeeping

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests and processes content from any file in the project directory based on the **/* glob pattern.
  • Ingestion points: The skill reads file content, directory structures, and git status outputs as described in SKILL.md.
  • Boundary markers: The instructions lack explicit boundary markers or directions for the agent to ignore instructions embedded within the files being processed.
  • Capability inventory: The agent is authorized to modify files, run git commands, and execute arbitrary project-defined scripts for verification and optimization.
  • Sanitization: No sanitization or validation steps are defined for content read from external files before processing.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands and project-specific scripts.
  • Evidence: The workflow explicitly directs the agent to run git status, git rm --cached, and to "Run existing verify scripts" and "optimize scripts" found within the repository. While standard for housekeeping, this allows for the execution of arbitrary code found within the data being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 01:00 PM
Security Audit — agent-trust-hub — housekeeping