NYC

wechat-converter

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes untrusted input ('通用写作 Skill 产出的内容') and possesses file-manipulation capabilities (Write, Edit). Without explicit boundary markers, an attacker providing the input content could embed instructions to manipulate files beyond the intended scope of conversion.
  • Ingestion points: Processes 'general writing content' as specified in the SKILL.md description.
  • Boundary markers: Absent. The instructions do not define specific delimiters (e.g., XML tags or triple quotes) to separate the content from the formatting instructions.
  • Capability inventory: Read, Write, Edit, Grep, Glob.
  • Sanitization: Absent. The skill instructions do not include steps to sanitize or ignore embedded commands in the source text.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:16 PM