skills/moejay/modspec/modspec-init/Gen Agent Trust Hub

modspec-init

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it is designed to read and process untrusted data from an existing codebase.
  • Ingestion points: The agent analyzes project structure, file contents, and directory boundaries in the target codebase.
  • Boundary markers: No specific delimiters are defined to isolate code content from instructions.
  • Capability inventory: The skill utilizes file system read access for analysis and file system write access for generating spec and feature files.
  • Sanitization: The instructions do not specify sanitization for the content processed from the codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 04:46 PM