pr
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_CONTEXT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The skill executes
git branchandgh pr viewat load time using the!syntax to initialize context. This is used legitimately to determine the current state of the workspace. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted PR template files from the repository.
- Ingestion points: Searches for and reads
pull_request_template.mdand files within.github/PULL_REQUEST_TEMPLATE/using theReadtool inSKILL.md. - Boundary markers: None. The skill does not instruct the agent to disregard instructions within these templates.
- Capability inventory: The agent can perform
git pushand use the GitHub CLI (gh) to create or edit PRs as defined inallowed-tools. - Sanitization: The skill lacks mechanisms to sanitize or validate the content of the ingested templates before including them in the PR body.
- [COMMAND_EXECUTION]: The skill uses standard developer tools (
git,gh) to push code and manage pull requests on GitHub, which is the intended use case. These commands are correctly scoped in the frontmatter configuration.
Audit Metadata