accept-web-renderer-prs
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes Pull Request diffs and Git history from external sources, which constitutes an ingestion point for untrusted data.
- Ingestion points: The skill ingests Pull Request diffs, Git history, and the content of 'packages/docs/docs/client-side-rendering/limitations.mdx'.
- Boundary markers: The skill does not employ explicit delimiters or instructions to ignore embedded commands in the PR data, which increases the risk of the agent following instructions found within the PR content.
- Capability inventory: The agent is granted the ability to push fixes to PRs, resolve merge conflicts, and perform the final merge of PRs.
- Sanitization: The skill lacks technical sanitization or input validation, relying instead on a high-level instruction for the agent to apply 'independent scrutiny'.
Audit Metadata