assign-target-to-sdr

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill incorporates user-provided name and email match strings directly into GraphQL and SOQL query parameters within SKILL.md. This ingestion of untrusted data into queries without explicit sanitization instructions creates a surface for indirect prompt injection if the user input contains control characters or if the returned record data contains malicious instructions meant to be interpreted by the agent.
  • Ingestion points: The %MATCH% placeholder in the GraphQL query for Contacts/Leads and SOQL query for BotVersions is populated by user input in Step 1.
  • Boundary markers: There are no explicit delimiters or instructions to ignore potential instructions embedded within the search terms or the returned data.
  • Capability inventory: The skill possesses the capability to perform write operations via the dispatch tool (POST to /services/data/v63.0/actions/standard/assignTargetToSdr) in Step 3.
  • Sanitization: The skill does not provide specific instructions for the agent to sanitize, escape, or validate the user-provided search strings before they are sent to the Salesforce API.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 06:39 PM