patrol-write-test
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a standard workflow for testing and uses authorized tools. All external links point to the author's official documentation (patrol.leancode.co). No malicious instructions, obfuscation, or unauthorized access patterns were detected.- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the application under test via the
patrol-native-treetool. Ingestion points: Native UI hierarchy retrieved in SKILL.md. Boundary markers: None mentioned for external UI data. Capability inventory: Test execution and management via tools likepatrol-runandpatrol-status. Sanitization: No specific sanitization of UI tree content is documented. This is assessed as safe as it is a core functional requirement for the skill's purpose.
Audit Metadata