weixin-extractor

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external WeChat URLs, which creates a vulnerability surface for indirect prompt injection. If an article contains malicious instructions, the agent processing the output might be influenced.\n
  • Ingestion points: The extract.py script and SKILL.md documentation define a workflow for processing remote WeChat URLs.\n
  • Boundary markers: The current placeholder implementation does not include delimiters or protective instructions to wrap the external content.\n
  • Capability inventory: The skill returns content to the agent, which may have capabilities like file system access or code execution.\n
  • Sanitization: No logic is present to sanitize or filter the content retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 05:04 PM
Security Audit — agent-trust-hub — weixin-extractor