meta-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 processes user-supplied campaign, audience, and asset data to generate creative briefs and ad copy, which creates a surface for indirect prompt injection.
- Ingestion points: External data enters the agent context via the campaign and audience arguments defined in the
argument-hint. - Boundary markers: The skill wrapper does not define explicit delimiters or instructions to isolate user-provided data from the workflow instructions.
- Capability inventory: The skill body does not contain evidence of file system writes, network operations, or subprocess execution capabilities.
- Sanitization: No input validation or content sanitization logic is present in the analyzed file.
Audit Metadata