add-pattern

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill creates a repository of design patterns from potentially untrusted input sources.
  • Ingestion points: The skill reads pattern descriptions and code examples from user prompts or conversation history.
  • Boundary markers: Absent. No instructions are provided to the agent to treat stored content as data only or to use delimiters to prevent instruction leakage.
  • Capability inventory: File-write operations to the local filesystem (patterns/ directory). The skill does not exhibit dangerous execution (eval/exec) or network capabilities.
  • Sanitization: Absent. There is no logic to filter or escape instructions embedded within the provided design patterns.
  • [Data Exposure] (SAFE): The skill only interacts with a specific local directory (patterns/) and does not access sensitive system paths or credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM