analyze-report

Warn

Audited by Snyk on Aug 22, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). Skill “analyze-report” ingests outsider-provided free text when the customer pastes a Mixpanel report/chart URL; at runtime it extracts IDs and fetches the report configuration and data to re-run the query (Step 1 Mode A and Step 2).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 1.00). The skill explicitly re-runs and fetches Mixpanel reports at runtime using URLs like https://mixpanel.com/project/<project_id>/view/<board_id>/app/, and that fetched report configuration/data is required to ground and directly control the agent's analysis prompts.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 22, 2026, 01:46 PM
Issues
2