muapi-ad-creative
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the muapi CLI tool and curl to interact with the service. These commands are used to configure authentication and perform the primary tasks of image generation and editing as intended by the skill's purpose.
- [EXTERNAL_DOWNLOADS]: The skill makes network requests to api.muapi.ai to process image generation requests. This is a functional requirement for the skill to operate and targets the service's dedicated API infrastructure.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input (product descriptions and audience details) and interpolates them into prompts for image and text generation.
- Ingestion points: User inputs product_or_service, target_audience, campaign_goal, and tone in SKILL.md.
- Boundary markers: No explicit delimiters or warnings are used to isolate user input in prompts.
- Capability inventory: The skill uses subprocess execution (muapi CLI) and network operations (curl to API) in SKILL.md.
- Sanitization: No specific sanitization or filtering logic is implemented within the skill itself.
Audit Metadata