wechat-draft-writer
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is entirely composed of Markdown and YAML files. There are no Python, JavaScript, or shell scripts included, which eliminates the risk of malicious code execution.
- [SAFE]: No prompt injection attempts, such as instructions to ignore safety guidelines or bypass restrictions, were detected in any of the skill's instructional content.
- [SAFE]: Regarding Indirect Prompt Injection: The skill ingests untrusted data from reference materials and voice transcripts (Ingestion points: SKILL.md, draft-dna-enforcement.md). While boundary markers and explicit sanitization are absent in the prompt structure, the skill lacks dangerous capabilities like subprocess execution, file system modification, or network operations, rendering the surface non-exploitable for technical attacks.
Audit Metadata