test-forge

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill implements standard software testing practices, including framework identification (reading package.json, go.mod, etc.) and the use of well-known libraries like fast-check or hypothesis.
  • [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves reading source code and project configurations, creating an attack surface for indirect prompt injection.
  • Ingestion points: Instructions in SKILL.md direct the agent to read the repository's code, existing tests, and dependency files.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded prompts in the source code are defined.
  • Capability inventory: The skill is authorized to write test files and execute testing/coverage commands (e.g., npm run cover, go test -cover) as per the SKILL.md workflow.
  • Sanitization: No specific sanitization methods for ingested code are described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 12:50 PM