skill-expert

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to run local Python scripts to initialize, validate, and package skills (e.g., python3 .agents/skills/skill-creator/scripts/quick_validate.py in SKILL.md). These commands are intended to run within the project's local directory structure.\n- [PROMPT_INJECTION]: The skill's primary function is the generation of new agent instructions (SKILL.md files) from user-provided data and project artifacts, which creates a surface for indirect prompt injection.\n
  • Ingestion points: User task prompts, use cases, runbooks, and project documentation are used as input for generating new skill content (SKILL.md).\n
  • Boundary markers: The instructions do not define boundary markers or safety wrappers to prevent the agent from obeying instructions embedded in the user-provided data.\n
  • Capability inventory: The skill involves writing files to the disk and executing shell scripts as part of its core lifecycle (SKILL.md).\n
  • Sanitization: There are no documented steps for the agent to sanitize or validate the user-provided input before it is incorporated into the generated skill's body.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 02:25 PM
Security Audit — agent-trust-hub — skill-expert