attribution
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill incorporates an indirect prompt injection surface by instructing the agent to read and follow context from project-specific marketing files.
- Ingestion points: The skill attempts to read
.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.mdfrom the project environment. - Boundary markers: No explicit delimiters or instructions to disregard potential malicious directives within these external context files are provided.
- Capability inventory: The skill possesses the ability to recommend marketing models, influence budget allocation strategies, and provide code snippets for web instrumentation and CRM synchronization.
- Sanitization: No sanitization or validation of the content within the marketing context files is specified.
- [EXTERNAL_DOWNLOADS]: The skill references an external tool registry and integration guides hosted on GitHub.
- Evidence: Multiple links in
SKILL.mdpoint tohttps://github.com/mbzadev/skills/blob/main/tools/REGISTRY.mdand related integration files. - Author Discrepancy: The repository URL uses the username
mbzadev, which differs from the attributed authormabzadevby the omission of a single character ('a'). This discrepancy represents a potential typosquatting or impersonation risk, although the referenced content appears to be technical documentation.
Audit Metadata