arkcli-gen
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data via text prompts and external media references, presenting an attack surface for indirect prompt injection.
- Ingestion points: The
promptpositional argument and--inputparameters (supporting local and remote files/URLs) used in thearkcli +gencommand acrossSKILL.mdandreferences/arkcli-gen.md. - Boundary markers: The instructions do not mandate the use of delimiters or specific safety framing when the agent interpolates user inputs into the tool command.
- Capability inventory: The skill is authorized to execute shell commands through the
arkclibinary, enabling network-based content generation, resource resolution, and local file management. - Sanitization: Input validation and safety filtering are delegated to the backend platform's risk detection systems (e.g.,
ContentRiskBlocked,SensitiveContentDetected) as noted in the error handling section ofSKILL.md.
Audit Metadata