infringement-triage
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Local File System Interaction: The skill reads from and writes to specific local directories (e.g.,
~/.claude/plugins/config/claude-for-legal/). This is a security consideration for file access, used to maintain matter context and practice profiles as part of the intended legal workflow. - Indirect Prompt Injection: The skill ingests user-provided descriptions of IP infringement to generate triage memos. As with any skill processing external data, there is a potential surface for instructions embedded in that data to influence agent behavior.
- Ingestion points: User-provided facts and exhibits reviewed during the intake process.
- Boundary markers: The skill employs a structured output format and prominent 'NOT A FINDING' headers to help maintain context.
- Capability inventory: The skill writes markdown files to local practice and matter folders.
- Sanitization: The skill relies on structured workflows and explicit disclaimers rather than programmatic input sanitization.
Audit Metadata