muapi-multi-angle-reshoot
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates user-provided text from the
subject_descriptionfield directly into the generation and editing prompts without sanitization or boundary markers. - Ingestion points:
subject_descriptioninput field in SKILL.md. - Boundary markers: Absent; user input is mixed directly with the prompt text used for image generation.
- Capability inventory: The skill uses the
muapiCLI andcurlfor subprocess calls to an external API. - Sanitization: None; the input is used as provided by the user.
- [COMMAND_EXECUTION]: The skill uses the
muapiCLI andcurlto interact with an external image processing API. These commands are necessary for the skill's functionality and target the vendor's infrastructure.
Audit Metadata