imagemagick
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted image media which can be used as a vector for malicious data or metadata targeting the agent or the image processing engine.
- Ingestion points: External image files provided for processing tasks in SKILL.md.
- Boundary markers: No delimiters or explicit instructions to ignore embedded content are specified to separate untrusted data from the agent's context.
- Capability inventory: The skill executes system commands via scripts/media_toolkit.py as defined in SKILL.md.
- Sanitization: No sanitization or validation logic is specified for the input files or command arguments.
- [COMMAND_EXECUTION]: The skill executes external tools through a local Python wrapper, creating a dependency on that script's implementation to prevent command injection from unsanitized input.
Audit Metadata