data-import

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill accesses files within the ~/.claude-marketing/ directory to load brand profiles and standard operating procedures (SOPs). This access is limited to the skill's specific application directory and is necessary for its primary function.
  • [PROMPT_INJECTION]: The skill processes untrusted data from external files and URLs, which represents a surface for indirect prompt injection.
  • Ingestion points: CSV, JSON, and Google Sheets URLs provided as arguments in SKILL.md.
  • Boundary markers: The instructions do not specify explicit delimiters or markers to separate ingested data from the agent's instructions.
  • Capability inventory: The skill reads local brand configuration files, writes data to external CRM and Email platforms via Model Context Protocol (MCP) servers, and executes a local script (competitor-tracker.py).
  • Sanitization: The skill effectively mitigates injection risks by disabling model invocation at the top level, performing strict data validation (e.g., email format RFC 5322), and requiring a mandatory human-in-the-loop approval gate that displays a summary of the data before any import occurs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 01:18 AM