marketing-skills-guide
Warn
Audited by Snyk on Feb 16, 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 explicitly directs the agent to "use WebFetch to retrieve the full README.md" from the public GitHub URL https://raw.githubusercontent.com/gmh5225/awesome-skills/refs/heads/main/README.md, which is a user-generated, public third-party resource the agent would fetch and read.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly tells the agent to use WebFetch at runtime to retrieve https://raw.githubusercontent.com/gmh5225/awesome-skills/refs/heads/main/README.md, a raw GitHub URL whose contents would be fetched and injected into the agent context and therefore can directly control prompts/resources.
Audit Metadata