campaign-copywriting
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingest untrusted data from external website URLs and strategy documents to generate email copy and machine-readable YAML files.\n
- Ingestion points: Researching provided Website URLs and strategy documents in SKILL.md.\n
- Boundary markers: The instructions do not define delimiters or warnings to ignore malicious instructions embedded in the input data.\n
- Capability inventory: The skill generates text and config files for filesystem storage (profiles/.../variants.yaml) and uses tools for external campaign uploading.\n
- Sanitization: There are no explicit sanitization steps for content retrieved from external sources before it is processed or used in file generation.
Audit Metadata