cmd-pr-build-context
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local
gitandgh(GitHub CLI) commands to identify the default branch, retrieve commit history, list files, and generate code diffs. These operations are essential for its stated purpose of building developer context. - [PROMPT_INJECTION]: The skill processes untrusted external data from the repository, including code diffs and documentation files such as
README.md,CLAUDE.md, andAGENTS.md. This creates a surface for indirect prompt injection where instructions hidden in the codebase could attempt to manipulate the agent's summary or analysis. - Ingestion points: Repository documentation files and git diff outputs.
- Boundary markers: No explicit delimiters or instructions are used to separate the ingested data from the agent's internal instructions.
- Capability inventory: Local shell command execution (
git,gh,sed) and repository file access. - Sanitization: The skill does not perform sanitization or validation of the content retrieved from the repository files.
Audit Metadata