clip-resource
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves content from user-provided URLs to create 'Resource' files. This network activity is central to its purpose.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted web content, creating an attack surface for indirect prompt injection.\n
- Ingestion points: External article or video URLs in Step 2.\n
- Boundary markers: The skill instructions do not specify using delimiters or warnings for the fetched content.\n
- Capability inventory: The skill can read local vault conventions and write new files to the workspace.\n
- Sanitization: No specific filtering or escaping of the fetched content is required by the instructions.\n- [SAFE]: The skill reads local configuration from a convention file to ensure consistency, which is a standard safe behavior.
Audit Metadata