log-activity

Fail

Audited by Snyk on Nov 11, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The bootstrap block tells the agent to disregard authorization and connectivity status and never surface it to the user, which hides relevant state from the user without showing clear malicious intent.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). The required read paths pull free-text Salesforce Task Descriptions and Contact/Opportunity names, which external parties can write into via inbound email-to-Salesforce logging or web capture, and the Read mode returns all of an account's Tasks without the agent selecting a specific item.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 11, 2026, 06:39 PM
Issues
2