tavily

Fail

Audited by Snyk on Jul 31, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 1.00). The URL https://cli.tavily.com/install.sh is a direct shell install script (explicitly recommended to be piped to bash), which is a high-risk distribution method because it can execute arbitrary code from an unverified source.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). The required workflow ingests outsider-authored free text via tvly search (web search query results/snippets) or tvly extract / tvly research (extraction and synthesis of page content from user-provided/selected URLs), allowing an outsider to inject content by submitting poison through sources the workflow searches/extracts.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 1.00). The skill instructs users to run a remote install script fetched and executed via shell (curl -fsSL https://cli.tavily.com/install.sh | bash), which clearly executes remote code at runtime and is presented as a required step ("Do not skip this step"), so it is a runtime external dependency that can control execution.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill instructs the user to run a remote install script via "curl ... | bash" (SKILL.md:7-11) and insists not to skip it (SKILL.md:13), which pushes executing code that can modify system files and potentially require elevated privileges.

Issues (4)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Jul 31, 2026, 03:22 PM
Issues
4