product-marketing-context

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses local project files such as README, package.json, and marketing documents to compile a product context. The gathered information is stored in a local file at .agents/product-marketing-context.md. No network operations or external data transmissions were identified.
  • [PROMPT_INJECTION]: The 'Auto-draft' feature processes untrusted content from the codebase, creating a surface for indirect prompt injection. Ingestion points: Project README, landing pages, and package.json. Boundary markers: Absent. Capability inventory: Local file system read/write for documentation purposes. Sanitization: None detected.
  • [COMMAND_EXECUTION]: No shell commands, subprocesses, or scripts are utilized by this skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 12:05 PM
Security Audit — agent-trust-hub — product-marketing-context