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

qa

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill is designed to ingest external specification and context files, creating a surface for potential instruction injection if those documents are compromised.
  • Ingestion points: Reads project-specific data from docs/dev/[feature-name]/SPEC.md and docs/dev/[feature-name]/CONTEXT.md as specified in SKILL.md.
  • Boundary markers: Absent; the instructions do not provide delimiters or warnings for the agent to distinguish between data and instructions within those files.
  • Capability inventory: The skill generates file-system artifacts (TEST_PLAN.md) and produces automated test code in SKILL.md.
  • Sanitization: No validation or sanitization of external content is defined before the agent processes it.
  • Dynamic Execution (LOW): The skill generates automated test scripts using frameworks like Vitest, Jest, and PyTest based on project specifications. This is a core functional feature but involves creating executable content from external inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:48 PM