fivem-dev
Warn
Audited by Snyk on Mar 4, 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's required workflow (SKILL.md and commands/fivem-dev.md) instructs the agent to WebFetch and parse live public documentation and community asset sites—e.g., https://docs.fivem.net/natives/ and the community-driven https://forge.plebmasters.de/—so it will ingest untrusted, user-contributed web content that can materially influence code generation and subsequent actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill repeatedly invokes WebFetch at runtime to retrieve authoritative docs (e.g., https://docs.fivem.net/natives/) using explicit fetch prompts that are injected into the agent flow, so external content is fetched during runtime and directly controls the agent's responses and is relied upon by the skill.
Audit Metadata