paper-write

Warn

Audited by Snyk on Nov 1, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). The workflow consumes an optional -- style-ref <source> argument pointing to arbitrary URLs or local files, but this is an opt-in search/fetch mechanism where the agent actively retrieves specific external material.

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

  • Potentially malicious external URL detected (medium risk: 0.30). The skill executes curl to fetch bibliography data from external repositories (dblp.org and doi.org) at runtime, which are common/reputable unofficial operational dependencies.

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
Nov 1, 2026, 01:42 AM
Issues
2