full-stop
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external pull requests, including diffs, reviews, and status checks, which represents a potential ingestion point for untrusted instructions.
- Ingestion points: Pull request metadata, branch diffs, and the referenced
full-sendskill instructions. - Boundary markers: The provided instructions do not specify any explicit delimiters or 'ignore' commands to protect the agent from instructions that may be embedded in the PR data it processes.
- Capability inventory: The skill can fetch branches, modify auto-merge settings, and execute the
unwatch_pull_requesttool. - Sanitization: There is no description of sanitization or filtering of the PR content before it is processed by the agent.
Audit Metadata