insurance-claims
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface detected. The skill is designed to systematically ingest and evaluate an entire codebase, which constitutes untrusted data that could contain malicious instructions.
- Ingestion points: Files in the current working directory across all phases (FNOL, Investigation, Adjustment, etc.).
- Boundary markers: Absent; the instructions do not wrap external content in delimiters or include 'ignore embedded instructions' warnings.
- Capability inventory: Read access to the local filesystem and write access to a local telemetry log file at
~/.claude/projects/skill-telemetry.md. - Sanitization: Absent; there is no logic to escape or validate data retrieved from the codebase before processing.
Audit Metadata