landing-page-copywriter
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of natural language instructions and structural templates. It does not execute scripts, access the network, or interact with the file system (other than reading its own reference template).
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided product details and audience descriptions to generate copy. While this constitutes an indirect prompt injection surface, there are no executable capabilities to abuse, making the risk negligible.
- Ingestion points: Product and service information input requested in
SKILL.mdStep 1. - Boundary markers: The skill uses a structured markdown template defined in
references/output-template.mdto format output. - Capability inventory: None; the skill is limited to text generation.
- Sanitization: No explicit sanitization of input data is performed beyond standard model guardrails.
Audit Metadata