ad-copy-generator
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates by taking user-provided arguments (offer, audience, platform, and objective) to generate structured ad copy. It relies on internal reference files for formatting and frameworks.
- [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data as it processes user input into generated ad variants. However, its restricted capability set (limited to Read/Write tools) and focused purpose pose no significant risk.
- Ingestion points: User-supplied arguments defined in
SKILL.md. - Boundary markers: No specific delimiters or safety instructions are defined for the input interpolation.
- Capability inventory: Access to
ReadandWritetools is specified in the YAML frontmatter. - Sanitization: No explicit sanitization or filtering is performed on the input data.
Audit Metadata