sales-call-prep-assistant

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWNO_CODE
Full Analysis
  • NO_CODE (SAFE): The skill consists entirely of Markdown text instructions. It does not include any Python scripts, Node.js packages, or shell commands.
  • PROMPT_INJECTION (SAFE): The instructions follow standard persona-based prompting without any attempts to override system safety filters or extract system prompts.
  • DATA_EXFILTRATION (SAFE): There are no patterns indicating access to sensitive local files (e.g., SSH keys, AWS credentials) or unauthorized network requests.
  • EXTERNAL_DOWNLOADS (SAFE): No remote URLs, package managers, or external scripts are referenced in the file content.
  • INDIRECT_PROMPT_INJECTION (INFO): While the skill is designed to process external data (company news, stakeholder info), it lacks any tools or capabilities (e.g., file-write, network-send, code-exec) to act on malicious instructions that might be embedded in that data. The risk is limited to content display.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 07:45 AM