imagemagick
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates processing external data which may be untrusted, leading to potential exploitation.
- Ingestion points: Processes images and PDFs from the local filesystem as indicated in the examples in SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded data are provided.
- Capability inventory: Extensive shell-based image processing capabilities using the magick tool suite.
- Sanitization: No explicit sanitization of input filenames or file contents is recommended to the agent.
- [COMMAND_EXECUTION]: The skill enables the agent to generate and execute shell commands for image processing, which requires caution when dealing with user-controlled input.
Audit Metadata