cloudinary-docs
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches documentation and technical guides from Cloudinary's official website.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests markdown documentation from external URLs, which represents a surface for indirect prompt injection.\n
- Ingestion points: URLs targeting Cloudinary's documentation (e.g., https://cloudinary.com/documentation/llms.txt) specified in SKILL.md.\n
- Boundary markers: The skill lacks explicit instructions or delimiters to isolate fetched content from the agent's core instructions.\n
- Capability inventory: No scripts or command execution capabilities were identified in SKILL.md.\n
- Sanitization: The skill does not provide methods for sanitizing or validating the retrieved data.
Audit Metadata