muapi-instagram-post
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a dedicated CLI tool
muapiand thecurlutility to perform image generation and status polling via the vendor's service. These commands are integral to the skill's stated purpose and operate within the vendor's ecosystem.- [EXTERNAL_DOWNLOADS]: The skill communicates withapi.muapi.aito send generation requests and retrieve assets. As this domain corresponds to the tool's specific service infrastructure, these network operations are considered safe and functional.- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text through thebriefandbrand_styleinputs, which are then interpolated into prompts for image and caption generation. While this presents a standard attack surface for large language models, the context of use is restricted to creative content generation.\n - Ingestion points: User inputs
briefandbrand_styledefined inSKILL.md.\n - Boundary markers: None present; user input is directly incorporated into the generated instructions.\n
- Capability inventory: Execution of
muapiCLI tools and network requests viacurlto vendor-owned endpoints.\n - Sanitization: No specific sanitization or filtering is applied to the input text before processing.
Audit Metadata