datasheet-reader

Warn

Audited by Snyk on Mar 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs running pcb scan on http(s) URLs (e.g., "pcb scan https://...") and then reading the generated markdown, so the agent fetches and interprets content from arbitrary public third‑party webpages/datasheets that could influence subsequent actions.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill runs pcb scan on arbitrary http(s) datasheet URLs (e.g., https://www.ti.com/lit/gpn/tca9554) at runtime and then ingests the converted markdown into the agent context, so fetched external document content can directly control prompts via prompt-injection and is a required dependency.

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
Mar 17, 2026, 10:00 PM
Issues
2