regression-testing
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted external data to drive its core logic and execution.
- Ingestion points: The skill ingests data from
changed_files(git diff),production_bugs(IDs and descriptions), andall_testsmetadata to perform test selection. - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded malicious content within the processed data.
- Capability inventory: The skill facilitates command execution through
npm runcommands (e.g.,npm run test:affected,npm run test:smoke) based on the results of the data processing. - Sanitization: There is no evidence of sanitization or validation of the input strings before they are used in test selection or CI/CD integration steps.
Audit Metadata