health-scoring
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes untrusted data from external sources such as CRM and support systems. 1. Ingestion points: CRM, support platform, and product analytics placeholders in SKILL.md. 2. Boundary markers: Absent; no delimiters or instructions to ignore embedded commands are present. 3. Capability inventory: None; the skill defines no scripts, command execution, or network calls. 4. Sanitization: Absent; no input validation is specified.\n- Instruction Safety (SAFE): No evidence of prompt injection, obfuscation, or persistence mechanisms was found.
Audit Metadata