getting-started
Fail
Audited by Snyk on May 22, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.80). Although most URLs are documentation/media (example.com) and look benign, the presence of a curl -fsSL https://cli.skillsrouter.sh | sh installer is a high-risk pattern (remote shell script piped to sh from an external domain without verification), making this a suspicious download/distribution vector.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly shows workflows that accept arbitrary external URLs as inputs (e.g., "Animate an Image", "Create a Talking Avatar", "Upscale a Draft" examples that use https://... media URLs), meaning the skill ingests untrusted third-party content which could materially influence processing and outputs.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The guide tells users to run a remote installer that is fetched and executed at install time via "curl -fsSL https://cli.skillsrouter.sh | sh", which executes remote code and is required to install the sr CLI used by the skill.
Issues (3)
E005
CRITICALSuspicious download URL detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata