ui-test-wait-strategy-review
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is strictly limited to static analysis and design review. It contains multiple explicit prohibitions against executing tests, modifying code, or accepting risk on behalf of a human.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which presents an attack surface. 1. Ingestion points: The agent is instructed to read user-supplied test code and network traces in prompts/ui-test-wait-strategy-review.md. 2. Boundary markers: The skill mandates a six-part input audit (known, missing, conflicting, stale, out_of_scope, and assumptions) and requires the agent to separate facts from inferences in its response. 3. Capability inventory: No tool execution, network exfiltration, or file-writing capabilities are authorized. 4. Sanitization: The skill relies on procedural validation and explicit audit steps to manage external content safely.
- [SAFE]: No patterns of data exfiltration, credential exposure, or persistence mechanisms were found. The skill does not perform network operations or access sensitive system paths.
- [SAFE]: No obfuscation techniques, multi-layer encoding, or hidden characters were detected in the skill instructions or supporting files.
Audit Metadata