content-atomizer

Fail

Audited by Snyk on Nov 17, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a content-repurposing workflow whose main risks are self-serving vendor promotion (a "we use Zernio" recommendation and a pay-per-call TREG_TOKEN aggregator pitch) rather than any attempt to attack or defraud the user, so it is sketchy but not malicious.

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

  • Third-party content exposure detected (medium risk: 0.30). The Engagement replies mode requires ingesting pasted comments or comments fetched from a post URL (via Firecrawl/WebFetch or TREG_TOKEN), and the agent triages all of them, so outsiders can post comments into a feed the workflow consumes without the agent selecting a specific item.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 17, 2026, 04:23 PM
Issues
2