skills/letta-ai/skills/ai-news/Snyk

ai-news

Warn

Audited by Snyk on Apr 23, 2026

Risk Level: MEDIUM

Full Analysis

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

Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests public RSS feeds and YouTube channel feeds/transcripts (see references/sources.md and scripts/fetch-news.ts plus scripts/fetch-transcript.ts and the SKILL.md workflow) and then the agent reads and synthesizes that content into digests, so untrusted third‑party/user‑generated content can influence its actions.

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Apr 23, 2026, 06:37 AM

Issues

1