agentic-quality-engineering

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a system that processes untrusted external data, such as Pull Request diffs and system logs, to drive automated testing and quality decisions.
  • Ingestion points: External content enters the agent context through parameters like prDiff in the Task tool and other data-processing functions within SKILL.md.
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within the coordination patterns, which could allow malicious code in a diff to influence agent behavior.
  • Capability inventory: The skill utilizes tools with significant privileges, including spawning autonomous agents using the Task tool, executing CLI commands (aqe), and writing to local persistent storage (aqe memory store).
  • Sanitization: No sanitization or validation mechanisms are described to filter or escape potentially malicious content from the ingested data before it is processed by the agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:23 AM
Security Audit — agent-trust-hub — agentic-quality-engineering