spec-generator

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands like find, ls, and cat to explore the directory structure and read file contents, which is necessary to generate specifications consistent with the existing project context.\n- [PROMPT_INJECTION]: The skill processes untrusted data from the local repository, creating a surface for indirect prompt injection.\n
  • Ingestion points: Project specification files and source code files.\n
  • Boundary markers: Absent; file contents are used directly as context.\n
  • Capability inventory: Local filesystem discovery and file reading.\n
  • Sanitization: No sanitization of ingested file content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 05:03 AM