investigation-open
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Local Configuration Access: In
SKILL.md, the skill is configured to load a specific file from~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md. This path is consistent with the tool's defined environment for legal investigation management. - Modular Skill Integration: The instructions utilize an
internal-investigationreference skill to handle substantive intake and templating, following a standard modular pattern for agent task delegation. - Data Ingestion Surface: The skill processes user-provided allegation descriptions to generate investigation documentation in
SKILL.md. - Ingestion points: allegation description passed via the
argument-hintfield inSKILL.md. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are present in the intake workflow.
- Capability inventory: File access to plugin configurations and invocation of reference skills in
SKILL.md; creation of persistent investigation logs. - Sanitization: The input is used directly to populate investigation checklists and templates.
Audit Metadata