automate-project-maintenance
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various development tools including rumdl, mise, nox, and biome to perform formatting, linting, and testing tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill processes repository configuration files (pyproject.toml, package.json) to determine the technology stack. This constitutes an ingestion point for external data that could influence agent behavior. 1. Ingestion points: Reads pyproject.toml and package.json in SKILL.md. 2. Boundary markers: None explicitly defined in the provided files to delimit data from instructions. 3. Capability inventory: Executes shell commands (rumdl, mise, nox, biome) and invokes other skills for file writing and GitHub synchronization. 4. Sanitization: No specific sanitization or validation of the file content is mentioned before branch logic is applied.
Audit Metadata