mage-ad-multiplier
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external media and user-defined headline text, creating an attack surface for indirect injection. It mitigates this by mandating the use of 'Static lock' and 'Video lock' instructions in every prompt, which act as clear boundary markers to protect sensitive elements like logos, products, and legal text from being altered by instructions embedded in the input data.
- [SAFE]: Analysis of the skill instructions and references reveals no malicious patterns. There is no evidence of obfuscation, unauthorized network exfiltration, or privileged command execution. All external resources, such as the Mage connector, belong to the verified vendor infrastructure.
Audit Metadata