copilot-pr-autopilot
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of build, test, and lint commands discovered from the repository's configuration files (e.g., package.json, Makefile). This is a core part of its functionality to ensure that automated fixes do not break the project's existing codebase.
- [PROMPT_INJECTION]: The skill processes untrusted input from pull request descriptions and review comments to guide its triaging and fixing actions, which creates a potential surface for indirect prompt injection. 1. Ingestion points: Pull request comments and descriptions are ingested through scripts/03-list-open-threads.ps1 and referenced in references/04-triage.md. 2. Boundary markers: No explicit delimiters or isolation techniques are implemented for these external inputs. 3. Capability inventory: The skill can execute shell commands, perform git commits and pushes, and execute GitHub API mutations. 4. Sanitization: No explicit content sanitization or filtering is performed on the ingested data.
Audit Metadata