pr-manual-testing
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
git diff main...HEADto retrieve code changes. This is a standard and expected operation for the primary purpose of identifying modified features for testing. - [PROMPT_INJECTION]: The skill processes untrusted data from pull request diffs to generate test cases. While this provides a surface for indirect prompt injection, the risk is low as the agent's actions are limited to generating structured Gherkin text.
Audit Metadata