wechat-title-optimizer

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • NO_CODE (SAFE): The skill consists entirely of natural language instructions (Markdown) and YAML metadata. There are no scripts, binaries, or automated tasks associated with this skill.
  • PROMPT_INJECTION (SAFE): No malicious override instructions or bypass attempts were detected. The instructions are strictly limited to the stated purpose of title optimization.
  • DATA_EXFILTRATION (SAFE): No network commands (e.g., curl, wget) or credential patterns (e.g., API keys, tokens) are present.
  • INDIRECT_PROMPT_INJECTION (LOW): The skill processes user-supplied article titles and content. While this represents an ingestion surface for untrusted data, the skill lacks any tool-use capabilities (file-write, network, or command execution) that could be exploited by an injection attack. Evidence Chain:
  • Ingestion points: User-provided '原标题' and '文章核心内容' (SKILL.md)
  • Boundary markers: Absent
  • Capability inventory: None
  • Sanitization: Not applicable for a text-only output skill
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 12:01 PM