content-research-writer

Fail

Audited by Snyk on Nov 22, 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 writing assistant with no malicious intent, but its example outputs present unverified statistics, quotes, and citations as researched findings without disclosing that the agent cannot verify them, which risks the user publishing fabricated claims.

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

  • Third-party content exposure detected (low risk: 0.10). The required research step has the agent search the open web and extract facts and quotes from results (SKILL.md lines 147-149), so outsider-authored pages are ingested only after the agent actively selects them, which is the low-risk pattern.

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 22, 2026, 01:13 AM
Issues
2