devfleet

Warn

Audited by Snyk on Nov 16, 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 get_report, get_mission_status, and get_dashboard output from the user's own local DevFleet instance, and those reports are generated from worktree agents that may read repo content, so they are at most a low-risk indirect path with no outsider submission route.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (medium risk: 0.30). The setup instructs installing and running the DevFleet server from the GitHub repo LEC-AI/claude-devfleet, then connecting via MCP, so the skill relies on that repo's code, which it executes. The repo belongs to an organization (LEC-AI) with no evidence of being a recognized vendor or established project, and the skill itself is marked community, so this is common but unofficial: medium. The localhost MCP endpoint is the local instance, not a separate remote source.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 16, 2026, 08:16 PM
Issues
2