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(inqeTestGenerator.generate) and external log files used for anomaly detection. - Boundary markers: Not explicitly specified in the instructions.
- Capability inventory: Spawns sub-agents through the
Tasktool and interacts with a persistent database via theaqeCLI. - 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