aqe-plan-quality

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from repository files including implementation code, tests, and AGENTS.md.
  • Ingestion points: Reading external repository files as specified in SKILL.md (Steps 1 and 2).
  • Boundary markers: No explicit delimiters or isolation instructions are used for the content read from the repository.
  • Capability inventory: A review of SKILL.md, agents/openai.yaml, and references/qe-routing.md shows no active capabilities like file writing, network requests, or shell execution.
  • Sanitization: No sanitization is performed on the ingested content.
  • [SAFE]: Step 4 in SKILL.md includes a protective instruction to avoid copying external agent syntax into the Codex environment, reducing the risk of accidental syntax-based injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 09:28 PM
Security Audit — agent-trust-hub — aqe-plan-quality