paid-ads-creative
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data via the platform, audience, and campaign arguments to generate creative briefs and ad copy.
- Ingestion points: User input provided through the argument-hint field is processed by the agent.
- Boundary markers: The skill does not implement delimiters or explicit instructions to treat the user-provided data as non-executable text.
- Capability inventory: This wrapper file does not define direct shell commands or network operations, but it inherits capabilities from the canonical skill file it references.
- Sanitization: No sanitization, filtering, or validation is performed on the user-supplied campaign data.
Audit Metadata