qe-agentic-quality-engineering

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data, such as pull request diffs and system logs, to generate tests and identify quality gaps. This creates a surface for indirect injection if malicious instructions are embedded in the code or logs being analyzed.
  • Ingestion points: prDiff (in qeTestGenerator.generate) and external log files used for anomaly detection.
  • Boundary markers: Not explicitly specified in the instructions.
  • Capability inventory: Spawns sub-agents through the Task tool and interacts with a persistent database via the aqe CLI.
  • Sanitization: No specific input sanitization or validation protocols are described in the instruction set.
  • [COMMAND_EXECUTION]: The skill utilizes a custom command-line interface, aqe, to manage agent memory (store/search) and track fleet metrics. These operations are restricted to the vendor's own namespace and local persistence layer (.agentic-qe/memory.db).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:15 PM
Security Audit — agent-trust-hub — qe-agentic-quality-engineering