copywriter
Warn
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends expanding its capabilities by installing a third-party plugin from the
coreyhaines31/marketingskillsGitHub repository using the marketplace add command. - [PROMPT_INJECTION]: The skill is designed to discover and ingest information from project-specific files such as
.agents/SYSTEM/ARCHITECTURE.mdand directories like.agents/SOP/to influence its writing behavior, which serves as a potential surface for indirect prompt injection attacks. - Ingestion points: Scans
.agents/SYSTEM/ARCHITECTURE.mdand the.agents/SOP/directory for context. - Boundary markers: The instructions do not define boundary markers or guidance to ignore malicious content embedded within the discovered project files.
- Capability inventory: Generates conversion-focused copywriting and adapts tone based on file contents.
- Sanitization: The instructions do not specify any validation or sanitization procedures for the data ingested from the project files.
Audit Metadata