Geek-skills-wechat-article-writer
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its core functionality of fetching and processing external content.
- Ingestion points: External data enters the agent context via the
web_fetchtool (used for website links) andweb searchresults, as specified inSKILL.mdunder 'Input Processing' and 'Content Research'. - Boundary markers: The instructions do not define any delimiters or explicit 'ignore instructions' warnings when processing fetched content.
- Capability inventory: The agent has the capability to generate long-form content and potentially write files (suggested formats include
.mdand.docxin the 'Fifth Step'). - Sanitization: There is no mention of sanitizing or filtering instructions from the retrieved content before it is used for article generation. This could allow a malicious website to influence the agent's output behavior.
Audit Metadata