mcp-servers-guide
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill describes a workflow to download generated media assets from PixelLab MCP server job URLs. This is an intentional feature of the asset generation process and the skill explicitly mandates local storage for safety.- [COMMAND_EXECUTION]: Instructions direct the agent to perform file system operations by saving downloaded assets into project directories like 'assets/' or 'public/images/'. This is a standard part of the asset integration workflow.- [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface through the use of visual analysis tools.\n
- Ingestion points: The 'analyze_screenshot' tool in 'SKILL.md' processes external visual data which may contain adversarial text.\n
- Boundary markers: None specified to distinguish screenshot content from instructions.\n
- Capability inventory: File system write operations are permitted for saving assets as defined in 'SKILL.md'.\n
- Sanitization: No sanitization or validation of screenshot content is mentioned.
Audit Metadata