copywriting-and-persuasion-expert
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's research workflow creates a surface for indirect prompt injection. It directs the agent to process data from external sources like Wikipedia and ArXiv and integrate them into its guidance without defining clear security boundaries for that data.
- Ingestion points: The
modules/research-checklist.mdfile explicitly instructs the agent to run web searches and capture external sources. - Boundary markers: The instructions do not specify the use of delimiters or provide warnings to the agent to ignore instructions that might be embedded within the researched content.
- Capability inventory: No dangerous commands, subprocess calls, or file-writing operations are present in the provided skill files.
- Sanitization: There are no instructions for sanitizing or filtering the content retrieved during the research phase.
Audit Metadata