sales-icp-definition

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted external data to automate the drafting of ICP artifacts, creating a potential attack surface for indirect prompt injection.
  • Ingestion points: The 'Interview' section in SKILL.md explicitly instructs the agent to offer to 'read the company's website, product docs, or CRM exports' to auto-draft a version for the user.
  • Boundary markers: The instructions lack specific guidance on using delimiters or 'ignore' instructions when processing these external data sources.
  • Capability inventory: The skill is primarily instructional and text-generating; while it does not contain direct command execution or network scripts, it generates structured artifacts (rubrics, checklists, plans) that influence sales strategy and downstream tools.
  • Sanitization: There are no documented procedures for sanitizing or validating the content extracted from external websites or files before the agent incorporates them into its reasoning context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 08:25 PM