agentic-quality-engineering
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data such as pull request diffs (prDiff) and code changes which introduces a surface for indirect prompt injection.
- Ingestion points: Pull request differences (prDiff) and code logs are ingested as input to various agents (e.g., qe-test-generator) in SKILL.md.
- Boundary markers: No explicit delimiters or system instructions to ignore instructions embedded within the ingested data are present in the provided examples.
- Capability inventory: The skill utilizes persistent memory storage (.agentic-qe/memory.db), agent spawning capabilities via the Task tool, and a command-line interface (aqe).
- Sanitization: No evidence of sanitization, escaping, or validation logic is defined for the ingested data before it is interpreted by the agent fleet.
Audit Metadata