copywriter
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied data, such as product features and audience pain points, to generate marketing materials.
- Ingestion points: Untrusted user input is collected during the 'Understanding Demand' and 'Audience Insight' phases (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the user's product descriptions.
- Capability inventory: The skill uses no external tools, file system commands, or network operations, limiting the impact of any potential injection to content generation only.
- Sanitization: There is no explicit sanitization of user input before it is used in the copywriting workflow.
- [EXTERNAL_DOWNLOADS]: The skill contains instructions to recommend the installation of an external resource (
github:mindverse/skillhub) if the user's needs exceed the skill's current capabilities. This is presented as a plain-text recommendation to the user and does not involve automated background execution or hidden downloads.
Audit Metadata