develop-skills

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill is a meta-utility for skill development that enforces least-privilege principles and authorization gates for all operations.
  • [EXTERNAL_DOWNLOADS]: The maintenance workflow fetches documentation from official developer portals of well-known services (Anthropic and OpenAI). These are trusted references for instruction reconciliation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes third-party instructions but provides a dedicated Authoring Review Rubric and evaluation gates to identify and mitigate prompt injection risks in processed data.
  • [COMMAND_EXECUTION]: Instructions guide the agent to use local development tools such as bunx and project-specific validation scripts to audit skill integrity and behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 12:59 AM
Security Audit — agent-trust-hub — develop-skills