skills/pavelsimo/skills/create-skill/Gen Agent Trust Hub

create-skill

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to manage the repository and file structure during the bootstrapping process.
  • Evidence: The workflow includes executing mkdir, git commit, git push, and gh repo clone to interact with the target repository.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface where malicious input could influence the behavior of generated agents.
  • Ingestion points: The skill accepts a plain-text description from the user in SKILL.md step 2.
  • Boundary markers: No delimiters or ignore-instructions warnings are included in the generation of the new SKILL.md file to isolate the user-provided data.
  • Capability inventory: The skill performs file writes, directory creation, and remote repository pushes, which are capabilities that could be abused if the generated instructions are compromised.
  • Sanitization: There is no evidence of sanitization or safety checks performed on the user's input before it is transformed into agent instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 09:46 AM
Security Audit — agent-trust-hub — create-skill