building-a-promotion-case
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): No malicious instructions or bypass attempts found.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No remote scripts or external packages are used.
- [Data Exposure & Exfiltration] (SAFE): No evidence of sensitive file access or data transmission.
- [Indirect Prompt Injection] (LOW): The skill processes user-provided promotion data (such as company rubrics and work examples) but lacks the capabilities (network, write, execute) to perform malicious actions if injected.
Audit Metadata