specs-setup

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs the user to fetch additional components from the author's official package repository (b12consulting/skills) via npx.
  • [COMMAND_EXECUTION]: Provides a manual command for the user to install missing dependencies using npx, which is a standard procedure for this modular skill set.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and analyze existing project code and documentation to generate new specification files.
  • Ingestion points: Processes existing project source code and README.md files in the current directory (SKILL.md, Step 3 and Step 6).
  • Boundary markers: Absent; the skill does not explicitly define delimiters or instruction-bypass warnings for the ingested project content.
  • Capability inventory: Includes file system write operations (creating .md files in the specs/ folder) and directory creation.
  • Sanitization: The skill relies on presenting drafted content to the user for review and explicit confirmation before finalization.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 07:56 AM