muapi-multi-angle-reshoot
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text through the
subject_descriptioninput and interpolates it directly into generative prompts for the image tools. - Ingestion points: The
subject_descriptionvariable is used in Phase A and subsequently referenced in Phase B. - Boundary markers: None. The input is placed directly into the prompt string without delimiters or instructions to the model to ignore embedded control characters.
- Capability inventory: The skill uses
muapi image generate,muapi image edit, andcurlto perform image operations and network requests. - Sanitization: No evidence of input sanitization or filtering was found in the instructions.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands via the
muapiCLI tool to perform authentication, image generation, and task polling. - [EXTERNAL_DOWNLOADS]: The skill makes network requests to
api.muapi.aiusingcurlto interact with the provider's image processing API when CLI aliases are unavailable.
Audit Metadata