lead-scoring

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing data from external, potentially untrusted sources.
  • Ingestion points: The skill ingests data from web search results (via search MCP), CRM records, and email platform data (via MCP) as specified in SKILL.md for the Timing and Engagement dimensions.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands or instructions within the retrieved external data.
  • Capability inventory: The skill is limited to generating formatted reports and routing recommendations; it does not possess high-risk capabilities such as arbitrary command execution, file system writing, or persistence mechanisms.
  • Sanitization: No evidence of data sanitization, escaping, or validation of the ingested external content was found in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 10:22 PM