inbound-lead-qualification

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by processing untrusted external content.
  • Ingestion points: Processes data from inbound-lead-data, raw CSVs, pasted text, and conversation transcripts (demo requests, chatbot logs) in SKILL.md (Step 1 and Step 5).
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore commands embedded within lead inputs.
  • Capability inventory: The agent is instructed to perform web-search, crm-lookup, and file system writes (Output CSV).
  • Sanitization: No sanitization, validation, or filtering of the lead-provided content is specified in the analysis workflow.
  • [NO_CODE]: The skill consists entirely of documentation and instructional content (markdown and JSON metadata); it does not include any executable Python, JavaScript, or shell scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:06 PM
Security Audit — agent-trust-hub — inbound-lead-qualification