reg-gap-analysis
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill is designed to read from a sensitive local file path:
~/.claude/plugins/config/claude-for-legal/privacy-legal/CLAUDE.md. This file contains sensitive organizational information, including privacy policy commitments, regulatory footprints, and internal system lists. While this is the intended functionality for the plugin, it represents access to sensitive data that could be exposed in the output. - [PROMPT_INJECTION]: The skill processes untrusted external data in the form of regulatory text or guidance pasted by the user or retrieved via research tools. This creates an indirect prompt injection surface where malicious instructions embedded in the regulatory text could attempt to influence the agent's analysis or output.
- Ingestion points: Regulatory text or summaries provided as arguments or pasted directly into the prompt in SKILL.md.
- Boundary markers: The skill lacks explicit boundary markers or delimiters to separate untrusted regulatory text from the agent's core instructions.
- Capability inventory: The skill has the capability to read local configuration files (CLAUDE.md) and save resulting documents to the local file system.
- Sanitization: No specific sanitization, filtering, or validation logic is defined for the ingested regulatory content.
Audit Metadata