create-agent-skill

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-provided input through the $ARGUMENTS variable and passes it directly to the create-agent-skills tool. This represents a functional surface for indirect prompt injection, as malicious instructions could be embedded in the user-provided description or requirements. However, this behavior is essential for the skill's primary purpose and no evidence of intentional bypass or malicious patterns was found in the skill's code.
  • Ingestion points: $ARGUMENTS in SKILL.md.
  • Boundary markers: None detected.
  • Capability inventory: Invokes the create-agent-skills tool.
  • Sanitization: No explicit sanitization or delimiting of the input variable before passing it to the tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 03:23 AM