automate-project-maintenance

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local commands rumdl, mise, nox, and biome to perform formatting, linting, and testing within the repository (SKILL.md).
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through repository contents.
  • Ingestion points: Reads and interprets pyproject.toml, package.json, and other repository files to determine the technology stack and maintenance steps (SKILL.md).
  • Boundary markers: Absent; there are no delimiters or warnings to ignore instructions embedded in the processed files.
  • Capability inventory: Has the ability to execute shell commands and modify repository files via child skills (SKILL.md).
  • Sanitization: Absent; the skill does not appear to validate or sanitize the data read from configuration files before using it to decide on actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 02:27 PM