landing-copy
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains no malicious code or instructions. It is designed for the legitimate purpose of copy optimization and follows standard marketing frameworks.
- [PROMPT_INJECTION]: The skill processes untrusted content from user-provided URLs or pasted text, creating an indirect prompt injection surface. The impact is negligible as the agent lacks high-risk capabilities like file system access or shell command execution.
- Ingestion points: Phase 1 (SKILL.md) describes fetching URLs and reading pasted text.
- Boundary markers: No specific delimiters are used to wrap external content.
- Capability inventory: The skill is limited to scoring text and providing rewritten copy.
- Sanitization: The skill does not define any sanitization or validation logic for external inputs.
Audit Metadata