sales-playbook

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill consists exclusively of Markdown documentation. No executable scripts (e.g., Python, JavaScript, Shell) or binaries are included in the package.
  • [PROMPT_INJECTION] (SAFE): The natural language instructions are task-specific and do not contain patterns intended to override agent safety protocols, reveal system prompts, or bypass constraints.
  • [DATA_EXFILTRATION] (SAFE): Although the skill references local context files (role.md, company.md) and external tool data (CRM, Knowledge Base), it lacks any mechanism such as network requests, file-writing commands, or subprocess execution to exfiltrate this information.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): The skill ingests untrusted data from external placeholders like 'knowledge base' and 'CRM'. However, because the skill has no tool-use or code execution capabilities, this ingestion surface cannot be exploited to perform unauthorized actions. Ingestion points: external tools and local files; Boundary markers: absent; Capability inventory: none; Sanitization: absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 03:54 PM