Skills
skills/extruct-ai/gtm-cowork-skills/key-account-plan/Gen Agent Trust Hub

key-account-plan

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface by ingesting and processing untrusted data from external sources which could contain malicious directives. \n
  • Ingestion points: Untrusted data enters the context via semantic-search-emails, get-email-content, google_drive_search, and get-call-recording. \n
  • Boundary markers: The instructions lack specific markers or delimiters to isolate untrusted data or warn the agent to ignore embedded instructions. \n
  • Capability inventory: The skill has the capability to write to external systems using create-note and create-task in the Attio CRM, and creates local files using the referenced docx skill. \n
  • Sanitization: There are no documented steps for sanitizing, filtering, or validating external content before it is used to populate CRM records or generated documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 06:20 AM