generate-test-spec
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
- [PROMPT_INJECTION]: The skill analyzes local source files to determine application functionality, which creates a surface for indirect prompt injection. Malicious instructions embedded in the project source code could manipulate the agent's output during the test generation process.
- Ingestion points: Local project source files (SKILL.md Step 1).
- Boundary markers: No specific boundary markers or 'ignore' instructions for code analysis are implemented.
- Capability inventory: The skill is capable of writing markdown files to the local .test/ directory.
- Sanitization: No explicit sanitization or validation of the content extracted from source files is performed.
- [CREDENTIALS_UNSAFE]: The skill workflow (Step 2) explicitly prompts the user to provide credentials and account states, which are then written into plaintext markdown files. This practice facilitates the storage of secrets in the project directory, increasing the risk of exposure if files are committed to version control.
Audit Metadata