image-resize
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch the agent-media package from the NPM registry during execution.
- [COMMAND_EXECUTION]: The skill executes shell commands via npx agent-media@latest to perform image resizing tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external URLs via the --in parameter, which may expose the agent to untrusted data. * Ingestion points: The --in parameter in SKILL.md accepts external URLs. * Boundary markers: No delimiters or ignore-instructions warnings are provided for the content retrieved from URLs. * Capability inventory: The skill has command execution and local file writing capabilities. * Sanitization: There is no mention of sanitization or validation of the input fetched from remote sources.
Audit Metadata