marketer-sync

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection through its data synchronization process.
  • Ingestion points: The skill retrieves external data from several remote MCP endpoints (e.g., strategies, analytics, and link lists) and saves this content into a local file at .10x/sync-data.json.
  • Boundary markers: There are no specified delimiters or instructions to the agent to disregard embedded commands when reading the cached JSON data to answer user questions.
  • Capability inventory: The agent performs network-read operations via MCP tools, file-write operations to save the cache, and file-read operations to extract information for the user.
  • Sanitization: The instructions do not define any sanitization or validation steps for the content fetched from the remote server before it is integrated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 10:10 PM
Security Audit — agent-trust-hub — marketer-sync