pr-summary
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The skill uses the dynamic injection syntax to run shell commands at load time, such as
gh pr diff,gh pr view,gh pr status, anddate. These are standard tools for providing pull request context and are used appropriately for a summarization tool.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external pull request data which could theoretically contain embedded instructions designed to influence the agent.\n - Ingestion points: Data is ingested from GitHub pull request diffs and comments via the
ghCLI commands inSKILL.md.\n - Boundary markers: The PR data is interpolated directly into the skill context without specific delimiters or isolation instructions.\n
- Capability inventory: The skill is restricted to gathering context for a summary and does not possess independent write access or external network exfiltration logic that would make injection particularly dangerous.\n
- Sanitization: The raw command output from the GitHub CLI is passed to the agent without further processing.
Audit Metadata