Skills
skills/pluginagentmarketplace/custom-plugin-software-design/design-patterns/Gen Agent Trust Hub

design-patterns

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The detect_antipattern action in SKILL.md accepts external code strings, which could contain instructions intended to manipulate the agent's output.
  • Ingestion points: code parameter for the detect_antipattern action defined in SKILL.md.
  • Boundary markers: Absent; no delimiters or instructions to ignore embedded commands are present in the skill definition.
  • Capability inventory: The skill's functionality is restricted to identification, generation, and teaching; it lacks access to sensitive system resources, network interfaces, or persistent storage in the provided implementation logic.
  • Sanitization: Absent; untrusted code is passed to the agent without filtering or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM