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${skill_name}is directly interpolated into commands such asgit checkout -b "add-${skill_name}-skill"andgit 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_namevariable is safe for shell execution.
Audit Metadata