pr-summary
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The script uses the
ghCLI to fetch PR data. This is an expected and safe operation given the skill's purpose. - [DATA_EXPOSURE]: PR data is fetched from GitHub and stored in a temporary Markdown file (
/tmp/pr-summary.md). No sensitive user credentials or system files are accessed. - [PROMPT_INJECTION]: The skill processes external data, creating a potential surface for indirect prompt injection.
- Ingestion points: PR titles and branch names are fetched in
scripts/pr-summary.shvia theghCLI. - Boundary markers: The output is structured into Markdown headers and blockquotes to separate PR content.
- Capability inventory: Limited to
gh(read-only PR list),bash(script execution), andcat(reading the temporary file). - Sanitization: PR metadata is handled as structured JSON data by
jqbefore being formatted into Markdown, preventing direct shell injection.
Audit Metadata