test-flakiness
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes test logs and result files which are external and potentially untrusted.\n
- Ingestion points: The skill reads logs from .github/, test-results/, and Unreal automation logs in Saved/Logs/ using Read and Grep tools.\n
- Boundary markers: No explicit delimiters or "ignore embedded instructions" warnings are defined to prevent the agent from following instructions potentially embedded in the logs.\n
- Capability inventory: The skill has access to Bash, Write, and Edit tools, allowing it to modify project files such as tests/regression-suite.md based on parsed log data.\n
- Sanitization: The skill does not implement sanitization or validation for the data read from external log files.\n- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to locate and list test artifacts.\n
- Evidence: Executes ls commands to find artifacts in standard locations like .github/ and test-results/.
Audit Metadata