wechat-writer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to perform environment setup and execute image generation scripts.\n - Evidence:
SKILL.mdcontains instructions to runpip3 installfor dependencies and executepython scripts/generate_image.pyto create article covers.\n- [EXTERNAL_DOWNLOADS]: The skill fetches content from external sources for research and interacts with third-party image generation services.\n - Evidence: Uses
WebFetchto retrieve articles for synthesis and calls official APIs from well-known technology providers withinscripts/generate_image.pyto generate visual content.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted data from the web.\n - Ingestion points: External web content is retrieved using
WebFetch(referenced inSKILL.md).\n - Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded in the fetched content.\n
- Capability inventory: The skill has access to
Bash(command execution) andWrite(file system access) tools.\n - Sanitization: No explicit sanitization or filtering of the retrieved content is mentioned before it is processed by the agent.
Audit Metadata