agentic-discovery
Fail
Audited by Snyk on Aug 11, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.90). These URLs include direct installers (shell and PowerShell) and a curl|bash endpoint hosted on inflowcli.ai—an unverified domain distributing scripts/executables—which is a high-risk pattern for malware delivery; the example.com endpoints are benign placeholders and not flagged.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). InFlow ODP discovery first runs
inflow odp directory searchusing a free-text--keyword, then fetches remote Service-provided catalog content (service descriptions/attributes/schemas/actions) and treats it as untrusted remote content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The SKILL.md recommends running installers that fetch and execute remote scripts (curl -fsSL https://inflowcli.ai/install.sh | bash, irm https://inflowcli.ai/install.ps1 | iex, curl -fsSL https://inflowcli.ai/cli | bash), which are runtime-install commands that execute remote code and are required to obtain the CLI dependency.
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