inno-rclone-to-overleaf
Warn
Audited by Snyk on Apr 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly uses pyoverleaf to read and download user-created Overleaf project files (see SKILL.md and the CLI examples like
pyoverleaf readand the "When pulling from Overleaf" workflow that downloads to /tmp, diffs, and instructs the agent to summarize and ask how to proceed), meaning untrusted third‑party project content is fetched and must be interpreted to drive decisions (merge/overwrite) — enabling indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata