change-documentation-rigor
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to locate and read pull request templates from the local repository (e.g.,
.github/pull_request_template.md) to use as a base for its output. If a repository contains a malicious template designed to hijack the agent's logic, the agent may follow those embedded instructions during the process of filling out the description. - Ingestion points: Template files located in
.github/,.gitlab/, or.bitbucket/directories within the active workspace, as specified in the repository template search logic inSKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the retrieved templates.
- Capability inventory: The agent is expected to execute shell commands (
git ls-files,grep) to find templates and perform file reads to process their contents. - Sanitization: No validation or sanitization is applied to the content of the discovered templates before they are used to structure the agent's response.
Audit Metadata