sqsl-wechat-start
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources, creating a vulnerability surface. (1) Ingestion points: WeChat article URLs and user-supplied files (Markdown and video) are ingested through the routing logic in SKILL.md. (2) Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded within the processed content. (3) Capability inventory: The specialized sub-skills perform file system writes (generating style modules) and external API interactions (WeChat draft box). (4) Sanitization: The routing logic does not specify any validation or sanitization for the data passed between components.
- [SAFE]: The skill includes documentation for configuring WeChat API credentials. It follows security best practices by instructing users to store sensitive keys (AppID, AppSecret) in a local configuration file (wechat_config.json) rather than hardcoding them.
Audit Metadata