skills/obra/clank/Creating Skills/Gen Agent Trust Hub

Creating Skills

Pass

Audited by Gen Agent Trust Hub on May 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely instructional and does not contain any executable scripts or code that could pose a security risk.
  • [SAFE]: No network operations, sensitive data access, or external downloads were identified.
  • [PROMPT_INJECTION]: The skill uses strong process enforcement language (e.g., "The Iron Law", "No exceptions", "MANDATORY") to guide the agent's behavior during skill creation. These are legitimate instructions for task performance and process compliance, not attempts to bypass safety filters or jailbreak the agent.
  • [COMMAND_EXECUTION]: References to standard command-line tools such as git, grep, wc, and npm are provided as examples of developer workflows and do not involve the automated execution of unsafe or unauthorized commands.
Audit Metadata
Risk Level
SAFE
Analyzed
May 30, 2026, 03:29 PM
Security Audit — agent-trust-hub — Creating Skills