herdr-runtime

Warn

Audited by Snyk on Nov 18, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). The required workflow reads Worker terminal output via herdr agent read (and agent prompt --wait), which can carry text from outsider-authored pages a Worker chose to fetch, but no outsider can POST into a queue the Supervisor monitors and the skill never forces the Worker to fetch specific outsider content.

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

  • Attempt to modify system services in skill instructions detected (low risk: 0.30). The skill mainly orchestrates Herdr terminal panes and top-level agents, which is project-scoped and does not involve sudo, user account creation, systemd, or SSH config. The one borderline item is that it suggests running herdr integration install for agents, which may write hooks into user-level agent configuration, so I'm flagging it at low-moderate severity under the recall-first instruction.

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 18, 2026, 05:10 AM
Issues
2