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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata