Skills
skills/frizzle-chan/mudd/add-verb/Gen Agent Trust Hub

add-verb

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (HIGH): The skill instructs the agent to run a shell command ./scripts/add_verb.py --action ACTION --verb VERB. If the agent populates these arguments from untrusted data, an attacker could use shell metacharacters to execute arbitrary commands.
  • [INDIRECT_PROMPT_INJECTION] (HIGH): The skill possesses a high-risk attack surface for indirect prompt injection and command injection.
  • Ingestion points: The ACTION and VERB parameters in SKILL.md are intended to be filled by the agent.
  • Boundary markers: None are specified; the skill does not instruct the agent to sanitize or quote the inputs.
  • Capability inventory: The skill enables shell command execution via the ./scripts/add_verb.py script.
  • Sanitization: No sanitization logic or validation instructions are provided in the skill documentation.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 07:56 AM