NYC

grief-companion

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill is vulnerable to indirect prompt injection because it ingests untrusted data while possessing high-capability tools. • Ingestion points: External content accessed via WebFetch and WebSearch tools, and user-provided narratives for memorial templates. • Boundary markers: Not present; there are no instructions to delimit or ignore potential commands within fetched or provided data. • Capability inventory: Includes powerful tools such as Bash, Write, Edit, and Task. • Sanitization: No explicit validation or sanitization procedures are defined for external data processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:03 PM