manage-skills

Warn

Audited by Snyk on Mar 18, 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). This SKILL.md explicitly instructs using public registries (e.g., "gitagent skills search" against the SkillsMP registry and GitHub and "gitagent skills install ... --provider github") to fetch and install third‑party skills (untrusted user-generated repos) which the agent will read/execute and can materially change tool use or behavior, enabling indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 09:52 AM
Issues
1