telegram-channel-parser
Warn
Audited by Snyk on Apr 1, 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 autonomously fetches and parses public, user-generated Telegram channel pages from t.me/s/ (see TG_BASE_URL in scripts/common.sh and the mandatory digest_json.sh + SKILL.md workflow that instructs the agent to run the fetch, read the produced JSON and inject it into assets/digest-feed.tsx), so untrusted third‑party post content is ingested and used to drive rendering/decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata