testgen
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local environment which could potentially contain malicious instructions intended to manipulate the AI's output.
- Ingestion points: The skill ingests content from local source files (
src/utils.ts,src/new-feature.ts), command output from version control (git diff), and structured coverage data (jq '.coverageMap'). - Boundary markers: External data is interpolated directly into prompts (e.g.,
"... $CODE ...") without using explicit boundary delimiters or 'ignore-instructions' headers to separate the code from the prompt instructions. - Capability inventory: The skill utilizes shell execution for test runners (
jest,vitest,mocha,stryker), file system access (cat,open), and network operations via thegeminitool to communicate with AI APIs. - Sanitization: No sanitization or escaping is performed on the ingested content before it is processed by the AI model.
Audit Metadata