sharing-skills

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
  • COMMAND_EXECUTION (MEDIUM): The skill instructs the agent to use shell variables in a way that is vulnerable to command injection.
  • Evidence: In SKILL.md, the variable ${skill_name} is directly interpolated into commands such as git checkout -b "add-${skill_name}-skill" and git commit -m "Add ${skill_name} skill".
  • Risk: If the agent processes a skill name containing shell metacharacters (e.g., ;, &, |, or backticks), it could lead to arbitrary command execution on the local system.
  • Sanitization: There are no input validation or escaping mechanisms described to ensure the skill_name variable is safe for shell execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 08:59 AM