policy-drafting
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a legal drafting tool, reading jurisdictional and matter-specific context from local configuration files within the plugin configuration directory. No malicious code, data exfiltration attempts, or unauthorized command executions were identified.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by reading configuration (
CLAUDE.md) and matter-specific files (matter.md) to inform its drafting process. This is a common pattern for such tools and is considered safe in this local context. - Ingestion points:
SKILL.md(references~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.mdandmatter.md). - Boundary markers: Absent. The skill does not implement delimiters or instructions to ignore potential commands embedded in the ingested files.
- Capability inventory:
SKILL.md(drafts policy text and writes to the local directory~/.claude/plugins/config/claude-for-legal/employment-legal/matters/). - Sanitization: Absent. No validation or filtering is applied to the ingested content.
Audit Metadata