qe-exploratory-testing-advanced

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data in the form of test charters, session notes, and findings documented during exploratory sessions. While this is necessary for its function, it creates a surface for indirect instructions to influence the agent.
  • Ingestion points: Session Note Template and Agent-Assisted Exploration inputs (charters, observations, findings) in SKILL.md.
  • Boundary markers: None present to delimit user/external findings from system instructions.
  • Capability inventory: Invocation of sub-tasks via Task() and coordination of multiple agents via FleetManager.coordinate() as shown in the examples.
  • Sanitization: No explicit sanitization or instruction to ignore embedded directives within session notes is provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:16 PM
Security Audit — agent-trust-hub — qe-exploratory-testing-advanced