studio-director

Warn

Audited by Snyk on Nov 20, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The required workflow's 48-hour results and "Lessons" review from distribution-lead (line 63) plausibly reads comments on the published videos, which outsiders can post without the agent selecting anything, so it is treated as a monitored feed under the recall-first override, though the skill never names comments explicitly.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill's only arguably operational change is that editor-apprentice saves learned editor and client skills, which configures the agent, but no explicit irreversible operational loss is established, so it fails the irreversible-loss gate.

Issues (2)

W011
MEDIUM

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

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 20, 2026, 04:51 PM
Issues
2