review-persona

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: 0.90). The skill's deep-review workflow explicitly composes with web-research components (SKILL.md and the "Integration with Other Skills" section state deep-review uses /dogpile and the skill lists dependencies like /ingest-youtube and /discover-movies), which indicates it will fetch and ingest public, user-generated web content (e.g., actor filmography, YouTube samples) that the agent is expected to read and use to drive review decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 17, 2026, 06:38 AM
Issues
1
Security Audit — snyk — review-persona