mage-angles
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed to interface with the Mage platform using specialized Model Context Protocol (MCP) tools for image generation and processing. All external links provided point to official vendor documentation and connector endpoints associated with the author.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data via image URLs and user-provided camera angle descriptions in SKILL.md. It utilizes a fixed prompt template for input interpolation but lacks explicit 'ignore embedded instructions' boundary markers. The capability inventory includes network operations via the 'generate' and 'get_request' tools, and file handling via 'create_upload'. To mitigate risks, the skill documentation includes explicit instructions for the agent to adhere to the platform's content filters and safety policies.
Audit Metadata