muapi-ad-creative

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided product descriptions and target audience information, which are then interpolated into prompts for image generation and ad copy creation. While this creates a surface for indirect prompt injection, it is standard for this type of creative generation skill.\n
  • Ingestion points: Input fields product_or_service and target_audience in SKILL.md.\n
  • Boundary markers: None present in the instructions to separate user input from system prompts.\n
  • Capability inventory: Execution of muapi CLI commands and curl requests to an external API.\n
  • Sanitization: No explicit sanitization or validation of the text inputs is defined in the skill.\n- [COMMAND_EXECUTION]: The skill uses shell commands and CLI tools (muapi, curl) to perform its primary functions, including image generation, editing, and authentication configuration. These actions are aligned with the skill's stated purpose.\n- [EXTERNAL_DOWNLOADS]: The skill interacts with the external domain api.muapi.ai to submit generation tasks and retrieve generated image assets. This network activity is necessary for the skill to function as an interface for the MuAPI service.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 11:15 PM