github
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill allows the agent to execute project-defined scripts for linting, testing, and building. This is an intended feature of the tool and is managed through instructions that encourage running only verified commands.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external project files (manifests, documentation) which could theoretically contain malicious instructions designed to influence the agent's behavior during the audit or publishing process.
- Ingestion points: Project manifest files (e.g., package.json, pyproject.toml) and documentation files (e.g., README.md) are read by the agent and the audit scripts.
- Boundary markers: No explicit delimiters are specified for file content ingestion, although the skill emphasizes minimal, evidence-based edits and non-negotiable safety rules.
- Capability inventory: The skill can execute shell commands via git and gh, and can perform local build/test operations through subprocess calls.
- Sanitization: The included remote_guard.py script automatically redacts credentials from Git remote URLs before displaying them.
Audit Metadata