gentle-ai-branch-pr
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data from GitHub repositories, specifically pull request templates (
.github/PULL_REQUEST_TEMPLATE.md) and issue descriptions/labels, to generate pull request content. This data could contain malicious instructions designed to influence the agent's behavior during the PR creation process. - Ingestion points: Pull request templates and GitHub issue metadata/descriptions are read to populate PR fields.
- Boundary markers: The skill does not define explicit delimiters or warnings to ignore instructions embedded within the ingested data.
- Capability inventory: The skill is capable of performing git operations (commit, push) and interacting with the GitHub CLI (create/edit PRs, add labels), though it requires explicit user authorization for each step.
- Sanitization: There is no evidence of sanitization or filtering of the content retrieved from external templates or issues before it is used in the prompt context.
Audit Metadata