pd-github-pr-summary
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a TypeScript file located at resources/pd-github.ts using 'npx tsx'. This is a standard mechanism for running scripts within the developer's local environment to fetch repository data.
- [PROMPT_INJECTION]: The skill processes external data from GitHub Pull Request metadata, representing a surface for indirect prompt injection.
- Ingestion points: Pull request titles and author metadata are retrieved via the GitHub API and processed by the script.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between PR content and system instructions.
- Capability inventory: The skill utilizes the Node.js runtime via npx for data processing.
- Sanitization: The skill focuses on displaying PR metadata; no specific sanitization of the fetched strings is described in the provided files.
Audit Metadata