overleaf-compile

Warn

Audited by Snyk on Jul 31, 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). In the required runtime workflow, the skill injects page-helpers.js into an already-open Overleaf project tab and then fetches build artifacts output.log / output.blg from Overleaf, which contain outsider-controlled LaTeX/Bib content authored in the project, and parse_log.py parses that text into structured messages.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 31, 2026, 01:29 PM
Issues
1
Security Audit — snyk — overleaf-compile