muapi-brochures
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interpolates user-controlled inputs (brand_name, topic, style, color_scheme, format) directly into prompts used for muapi image edit and muapi image generate in SKILL.md.
- Ingestion points: User inputs defined in the YAML header and Inputs table.
- Boundary markers: Absent; inputs are placed directly within the text of the tool prompts.
- Capability inventory: Includes network access via CLI and curl to the api.muapi.ai endpoint.
- Sanitization: No input validation or escaping logic is described in the instructions.
- [COMMAND_EXECUTION]: The skill defines workflows that require the agent to execute shell commands (muapi CLI, curl) to interact with external APIs. It specifically instructs the agent to use curl for endpoints not yet supported by the CLI, passing the API key via a header.
Audit Metadata