wechat-channels-research
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external WeChat Channels content, such as video comments and user profiles, which could contain hidden instructions targeting the agent.
- Ingestion points: Data is retrieved through tools such as
wechat_channels_v2_video_comments,wechat_channels_v2_user_profile, andwechat_channels_v2_video_detailas listed inSKILL.mdandreferences/sandbase-api-map.md. - Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are defined in the instructions.
- Capability inventory: The tools provided are restricted to read-only research operations; no file-writing or system command execution capabilities are present in the skill.
- Sanitization: There are no explicit instructions for the agent to sanitize or escape the content fetched from the external platform.
Audit Metadata