update-pr-summary
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions intended to hijack the agent's behavior.
- Ingestion points: Fetches PR title, body, and diff content using
gh pr viewandgit diff/gh pr diff(SKILL.md, steps 1 and 2). - Boundary markers: None identified. The skill does not use delimiters or instructions to ignore potential commands embedded in the PR data.
- Capability inventory: The agent has the ability to modify repository content by executing
gh pr edit(SKILL.md, step 4). - Sanitization: No evidence of sanitization or validation of the fetched PR content before it is processed and used to generate a new PR summary.
Audit Metadata