soia-pkm-clip-wechat-article

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external WeChat URLs, which could potentially contain malicious instructions targeting the AI agent.
  • Ingestion points: The scripts/archive_wechat.py script fetches HTML content from external mp.weixin.qq.com URLs provided as input.
  • Boundary markers: The extracted article content is wrapped in Markdown headers (## 原文) and YAML frontmatter delimiters, though it lacks an explicit warning for the agent to ignore instructions within the clipped text.
  • Capability inventory: The skill has the capability to write files to the local filesystem (Obsidian vault) via the atomic_write_text function.
  • Sanitization: The script uses a custom HTMLParser to extract specific article components while ignoring script and style tags. It also performs YAML escaping on metadata fields and uses strict path resolution to ensure files are only written within the designated vault.
  • [EXTERNAL_DOWNLOADS]: The SKILL.md file suggests installation via npx and the claude plugin marketplace using packages associated with the vendor (soia-team). These references are consistent with the skill's stated provenance and installation workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 03:51 AM
Security Audit — agent-trust-hub — soia-pkm-clip-wechat-article