skills/keiji-miyake/agent-skills/qa/Gen Agent Trust Hub

qa

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines a legitimate Quality Assurance role for testing software, creating test plans, and automating tests using industry-standard tools like Vitest and PyTest. No security violations were found in the instructions.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation files which acts as a potential surface for indirect injection, though it is standard for this type of assistant.\n
  • Ingestion points: Reads documentation from docs/dev/[feature-name]/SPEC.md and docs/dev/[feature-name]/CONTEXT.md.\n
  • Boundary markers: None; the instructions do not specify the use of delimiters for external content.\n
  • Capability inventory: Writing documentation (TEST_PLAN.md) and generating automated test code.\n
  • Sanitization: No sanitization is performed on ingested file content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:20 AM