NYC

blueprints-writing

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns, such as prompt injection, data exfiltration, or unauthorized command execution, were found in the skill instructions. The skill utilizes a set of local tools for file management and documentation that are consistent with its stated purpose.
  • [Indirect Prompt Injection] (LOW): The skill functions as a documentation assistant that processes external technical data to generate files, which is a standard operational surface.
  • Ingestion points: Technical descriptions and codebase contents accessed via tools like Read and Grep.
  • Boundary markers: Absent; the instructions do not specify delimiters for untrusted input when interpolating into templates.
  • Capability inventory: File creation and modification capabilities (Write, Edit, and mcp__plugin_hashi-blueprints_blueprints__write_blueprint).
  • Sanitization: Absent; the skill relies on the agent's inherent processing of technical text without specific escaping logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 07:51 PM