wechat-article-writer
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests potentially untrusted data from the user-provided material library in the
my-articles/directory and from external search results during the Market Research phase. This data influences the creation of themy-style.mdprofile and the generation of article content. - Ingestion points:
my-articles/directory and external fetch operations during Phase 2 (Market Research). - Boundary markers: Absent; there are no specific instructions or delimiters used to prevent the agent from executing instructions found within the ingested content.
- Capability inventory: File system write access (
my-style.md,creation-log.md), article generation, and invocation of external skills for media creation. - Sanitization: Absent; the skill does not specify any validation or filtering of external content before processing.
Audit Metadata