media-generation
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation and use of the
agentcashpackage from the NPM registry to facilitate API requests and payment handling. - [COMMAND_EXECUTION]: Shell commands are executed via
npx agentcash@latestandcurlto interact with remote endpoints and perform binary file uploads. - [DATA_EXFILTRATION]: User-provided prompts and local image files are transmitted to external services including
stablestudio.devand Vercel Blob storage for processing and hosting. - [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface by interpolating untrusted user prompts directly into API request bodies without explicit sanitization or boundary markers. 1. Ingestion points: User-provided prompts in the
promptfield of generation and edit requests (SKILL.md). 2. Boundary markers: None identified in the provided instructions. 3. Capability inventory: Network communication and file transmission via theagentcashCLI andcurl(SKILL.md, rules/uploads.md). 4. Sanitization: No sanitization or validation of user-provided prompt content is specified.
Audit Metadata