post-to-xhs
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses WebFetch to extract content from user-provided URLs to populate the post details. This creates a risk where malicious instructions embedded in the external web content could attempt to influence the agent's actions. The skill mitigates this by enforcing a human-in-the-loop confirmation step where the user must review the content before publication.
- Ingestion points: File SKILL.md in the content validation section where WebFetch is used.
- Boundary markers: No specific delimiters or boundary warnings are defined in the instructions for the fetched content.
- Capability inventory: The skill utilizes the publish_content and publish_with_video tools to send data to the Xiaohongshu platform.
- Sanitization: The skill performs length checks on the title and path format checks for local files, but relies primarily on user confirmation to prevent unintended actions.
Audit Metadata