mercury-journal-entry-prep

Warn

Audited by Snyk on Jun 13, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). The skill fetches Mercury transaction details at runtime (including counterpartyName, category, note, and attachments via mercury transactions list/get --format jsonl), and those fields are outsider-authored free text from third parties (e.g., vendor/customer names and transaction notes) that are then inserted into the generated Markdown workpaper and thus into the agent’s LLM context.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 13, 2026, 12:52 PM
Issues
1