muapi-storyboard
Warn
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill relies on a custom CLI tool named muapi which is not a verified package or part of a trusted ecosystem.\n- [COMMAND_EXECUTION]: The skill executes shell commands using the muapi CLI and curl for image generation and API interactions.\n- [DATA_EXFILTRATION]: The skill transmits the MUAPI_API_KEY environment variable to the api.muapi.ai domain via curl. While this is used for authentication, the destination is an external domain not included in the verified list.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied premise text and interpolates it into generation prompts and API calls without sanitization or boundary markers.\n
- Ingestion points: The premise input field in SKILL.md.\n
- Boundary markers: No delimiters or instructions are provided to the agent to treat the input as untrusted data.\n
- Capability inventory: The skill can execute shell commands (muapi, curl) and perform network operations.\n
- Sanitization: No input validation or sanitization steps are defined.
Audit Metadata