Skills
skills/jabrena/cursor-rules-java/031-architecture-adr-functional-requirements/Gen Agent Trust Hub

031-architecture-adr-functional-requirements

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the date command in the terminal to obtain an accurate timestamp for the ADR documentation.
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by analyzing untrusted files in the user's workspace using list_dir, file_search, grep, and codebase_search to infer project architecture. Ingestion points: Codebase files in the current workspace. Boundary markers: Absent. Capability inventory: File system access and shell execution (date). Sanitization: Absent. This behavior is standard for the skill's primary purpose of analyzing software projects.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 06:06 PM