learn-pattern
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to automatically detect and apply patterns from the user's project, creating a surface for indirect prompt injection attacks if the processed data contains malicious instructions disguised as patterns.
- Ingestion points: The entire user project as specified in the description ('Detect recurring patterns in user's project').
- Boundary markers: No explicit boundary markers or instructions to ignore embedded prompts are defined in the skill logic.
- Capability inventory: The skill has the capability to write or apply changes automatically to the project environment ('apply_automatically').
- Sanitization: There is no evidence of input validation or sanitization for the patterns learned from the project files.
Audit Metadata