muapi-social-pack
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text through the
caption_ideainput, which is directly interpolated into the instructions sent to the image editing model. - Ingestion points:
SKILL.mddefinescaption_ideaas a text input. - Boundary markers: The prompt template does not use specific delimiters or escape sequences to isolate user input from the rest of the instruction.
- Capability inventory: The skill executes
muapi image editcommands andcurlrequests to the vendor's API. - Sanitization: No explicit sanitization or validation of the input text is performed before interpolation.
- [COMMAND_EXECUTION]: The skill instructions include usage of the
muapiCLI tool andcurlfor interacting with the service provider's API. These operations are restricted to the vendor's official endpoints (api.muapi.ai) and represent standard operational behavior for the skill's stated purpose.
Audit Metadata