clidev

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: 1.00). The SKILL.md and README explicitly instruct the agent to fetch and use a public GitHub repository (git clone https://github.com/cedanl/clidev-presentaties.git) and to install external packages/skills (npx skills add, npm install), so the agent will ingest untrusted, user-controlled third-party content that can influence its behavior (templates, CLAUDE.md, scripts) during the workflow.

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

  • Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs cloning/installing a remote repository at runtime (e.g., git clone https://github.com/cedanl/clidev-presentaties.git and npx skills add cedanl/clidev-presentaties), and that repository (CLAUDE.md / theme / scripts) is relied on to provide guardrails and project code that the agent uses to generate presentations — meaning remote content fetched at runtime can directly control prompts and execute code.

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
Mar 17, 2026, 10:07 AM
Issues
2