chinese-legal-research-cn
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and follow instructions from external files located in
legal-research-cn/CLAUDE.mdandskills/*/SKILL.md. This architecture creates a vulnerability surface where malicious instructions in those files could be executed by the agent. - Ingestion points:
legal-research-cn/CLAUDE.md,legal-research-cn/skills/*/SKILL.md(referenced in SKILL.md). - Boundary markers: Absent. The skill does not include instructions to treat external content as untrusted or provide delimiters to isolate external data.
- Capability inventory: The skill instructions (SKILL.md) explicitly direct the agent to use tools for local file access, web verification, and document rendering.
- Sanitization: Absent.
- [DATA_EXFILTRATION]: The skill instructs the agent to access and read configuration profiles from the user's home directory at
~/.claude/plugins/config/.... While this is functional for an adapter, it represents access to application data outside the immediate project workspace.
Audit Metadata