client-comms-log
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external data (client communications) stored in log.md files.
- Ingestion points: Case-specific communication logs located at
~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[案件编号]/log.md. - Boundary markers: None present to distinguish between log data and system instructions.
- Capability inventory: Ability to read/write files and execute related agent commands like
/deadlinesor/client-letter. - Sanitization: No evidence of escaping or filtering content retrieved from the logs before processing for summaries or patterns.
Audit Metadata