anthropics-pptx

Warn

Audited by Snyk on Mar 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill's pptxgenjs.md (referenced from SKILL.md as part of the required "create from scratch" workflow) explicitly allows adding images/backgrounds from arbitrary URLs (e.g., slide.addImage({ path: "https://example.com/image.jpg" }) and slide.background { path: "https://example.com/bg.jpg" }) and the SKILL.md QA flow requires visually inspecting slide images, so the agent can fetch and then read/interpret untrusted third‑party content that could influence editing decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 15, 2026, 08:18 AM
Issues
1