stability-ai
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the
@membranehq/clipackage, which is installed from the official npm registry. This CLI tool is a standard resource provided by the vendor to facilitate API integrations. - [COMMAND_EXECUTION]: The instructions include several shell commands using the
membraneCLI andnpxto manage authentication, poll connection statuses, and execute generative AI actions. - [INDIRECT_PROMPT_INJECTION]: The skill processes generative output and metadata from the Stability AI API, which creates a surface for potential indirect instructions.
- Ingestion points: Data returned from generative actions like
txt2img,img2img, and direct proxy requests (SKILL.md). - Boundary markers: The skill does not specify delimiters or explicit instructions for the agent to ignore potentially malicious content within API responses.
- Capability inventory: The agent can execute CLI commands, perform network requests through a proxy, and run various actions via the
membranetool (SKILL.md). - Sanitization: No explicit sanitization or validation of the external API content is defined in the skill logic.
Audit Metadata