pr
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources such as git diffs, issue specifications, and project plans to generate pull request summaries.
- Ingestion points: The skill ingests authoritative specs, issues, ticket graphs, and git diffs (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded malicious content within the analyzed inputs.
- Capability inventory: The skill involves creating and updating pull requests via the GitHub CLI (
gh) or a referenceddraft-pull-requestworkflow. - Sanitization: No explicit sanitization or filtering of input data is defined before it is formatted into the PR body.
- [SAFE]: The skill consists entirely of markdown instructions and does not include any scripts, executable code, or network-enabled operations in the analyzed file.
Audit Metadata