gsd-to-autoforge-spec

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill reads data from local markdown files and package.json to synthesize a new project specification, which could allow malicious instructions in those source files to influence the downstream AutoForge agent.
  • Ingestion points: Documents located in the .planning/codebase/ directory and the package.json file.
  • Boundary markers: Absent; the skill does not use specific delimiters or instructions to ignore embedded commands when processing external content into the generated spec.
  • Capability inventory: The skill performs basic file system operations including directory creation (mkdir), file reading (cat), and file writing (cat >).
  • Sanitization: Absent; no explicit sanitization, escaping, or validation of the input content is performed before interpolation into the generated output file.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 05:25 AM