shift-left-testing
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill inherently processes untrusted external data during its core workflows, such as reviewing pull requests and refining user stories.
- Ingestion points: External data enters the context through Pull Request code reviews, user stories during sprint planning, and the
.agents/qa-project-context.mdfile. - Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings for the external content being analyzed.
- Capability inventory: The skill facilitates file reading and writing (e.g., updating
.github/pull_request_template.md) and assumes the agent has basic shell capabilities for verification. - Sanitization: No evidence of input validation or sanitization is present in the instructions for processing user-supplied code or requirements.
- [COMMAND_EXECUTION]: The skill includes shell command instructions for environment verification.
- Evidence: The Verification section provides commands (
test -f .github/pull_request_template.md && grep -qi "unit test" .github/pull_request_template.md) to be executed by the agent to confirm repository setup.
Audit Metadata