account-plan
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 skill's connectivity bootstrap tells the agent to treat any response, including a 500 error, as proof of connectivity and to suppress user-facing authorization or connection warnings, which hides real limitations from the user without any sign of malicious intent.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The create path's required C2 step runs an instructed web research pass (line 105) to ground competitors, industry trends, and priorities, which reads arbitrary outsider-authored web pages the agent must actively search for, while the Salesforce Account, Opportunity, and Task reads are own-tenant CRM data.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata