Customer Onboarding
Pass
Audited by Gen Agent Trust Hub on Feb 14, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [Data Exposure & Exfiltration] (SAFE): No file system access or network operations were found in the skill files. The skill is entirely text-based.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill contains no code files, scripts, or dependency manifests (e.g., package.json, requirements.txt).
- [Indirect Prompt Injection] (LOW): While the skill processes user-supplied business context to generate onboarding materials, it lacks the capabilities (such as command execution or file modification) required for an attacker to escalate an injection into a system-level threat.
- [Metadata Poisoning] (SAFE): Metadata in SKILL.md and _meta.json is descriptive and does not contain hidden instructions or malicious payloads.
Audit Metadata