skills/howells/arc/legal/Gen Agent Trust Hub

legal

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by ingesting untrusted content from the user's codebase to inform its generation process.
  • Ingestion points: The skill performs a comprehensive scan of codebase files in Step 2, including source code, database schemas (e.g., Prisma, Drizzle), and documentation (e.g., docs/progress.md).
  • Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent ignores or isolates potential instructions embedded within the files it reads during the project detection phase.
  • Capability inventory: The agent utilizes file reading tools and has the capability to generate and suggest the creation of new project files (Step 5) based on the scanned data.
  • Sanitization: No sanitization or validation logic is specified for the data extracted from the codebase before it is interpolated into the legal document templates in Step 4.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 06:17 AM