anycap-cli
Fail
Audited by Snyk on Mar 31, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.90). The URL https://anycap.ai/install.sh is suspicious because it points to a shell installer on an unfamiliar domain and the prompt advocates curl | sh (direct execution of remote scripts is a high-risk distribution vector), while https://example.com/photo.jpg is just a benign placeholder image and low risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's actions and download commands explicitly accept arbitrary public URLs (e.g., references/actions.md shows anycap actions image-understand --url https://example.com/photo.jpg and video-read --url https://example.com/clip.mp4, and anycap download in references/cli-reference.md), meaning the agent will fetch and interpret untrusted third-party content which can materially influence subsequent tool use and decisions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill's install step executes a remote shell script via "curl -fsSL https://anycap.ai/install.sh | sh", which fetches and runs remote code and is presented as the required way to obtain the AnyCap CLI.
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