tavily Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower

Source:

SHA-256:

tavily is an AI agent skill, created by arun-8687 and published at openclaw/skills. ClawSecure audited tavily across 4 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 75/100 (Medium Risk). The 5 findings concentrate in Policy Violation, Data Exfiltration and Permissions Manifest, including Only 46% of skill content could be analyzed. 2 of 4 files… and Suspicious Pattern: fetch(. 1 was rated high or critical severity.

Is tavily safe?

ClawSecure audited tavily and assigned a security score of 75/100 (Medium Risk), identifying 5 findings across Policy Violation and Data Exfiltration. Review the findings below before installing.

What did ClawSecure find in tavily?

ClawSecure identified 5 findings in tavily, concentrated in Policy Violation, Data Exfiltration and Permissions Manifest. 1 was rated high or critical severity. The most severe include Only 46% of skill content could be analyzed. 2 of 4 files… and Suspicious Pattern: fetch(.

How was tavily audited?

ClawSecure ran tavily through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 4 files from openclaw/skills.

What does a score of 75 mean?

ClawSecure assigned tavily a security score of 75/100, placing it in the Medium Risk range. This reflects 5 findings led by Policy Violation that warrant review before production use. ClawSecure derives this score with a weighted deduction model (critical -20, high -10, medium -5, low -2 from a base of 100).

Audit Findings for tavily

ClawSecure detected 5 security findings in tavily, spanning Policy Violation, Data Exfiltration and Permissions Manifest.

high · Only 46% of skill content could be analyzed. 2 of 4 files…. Policy Violation finding.
medium · Suspicious Pattern: fetch(. Data Exfiltration finding detected in scripts/extract.mjs:24.
medium · Suspicious Pattern: fetch(. Data Exfiltration finding detected in scripts/search.mjs:62.
medium · Missing config.json - agent may not be properly configured. Permissions Manifest finding.
info · Missing License Declaration. Policy Violation finding detected in SKILL.md.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for tavily

Resolve policy violations

tavily trips ClawSecure policy checks. Review each flagged pattern against your security policy and remediate or document an accepted exception before production use.

Audit external network connections

tavily sends data to external endpoints. Confirm each destination is expected and authorized, and remove any callback that exfiltrates data. ClawSecure monitors for known exfiltration and C2 endpoints.

Add a config.json permissions manifest

A config.json file declares what an agent component can access: file system, network, shell execution and more. Without it, users have no visibility into what the component can do before installing. This is the single most impactful security improvement for any AI agent skill.

Pin dependencies to exact versions

Unpinned dependencies allow supply-chain attacks where a compromised version is pulled in automatically. Use exact version numbers in package.json (for example 1.2.3 instead of ^1.2.3) to keep unauthorized code out of your dependency tree. ClawSecure checks every dependency against known CVE databases.

Related Security Research

OWASP ASI Top 10 Explained: The Complete Guide to AI Agent Security Standards→Understanding Our 3-Layer Audit Protocol→ClawHavoc Explained: The Malware Family Targeting AI Agents→

Related AI Agent Security Audits

a2aScore 85/100 a2aScore 85/100 @martian-engineering/lossless-clawScore 85/100 @martian-engineering/lossless-clawScore 85/100 @martian-engineering/lossless-clawScore 85/100

Scanned on March 8, 2026. tavily is one of thousands of agents audited by ClawSecure from the community-curated awesome-openclaw-skills list and the openclaw/skills repository.

Start Your Free Scan