← Back to Scanner

"Deep Research" Security Audit Report

🔭 Continuously monitored by ClawSecure Watchtower
Source:
SHA-256:

"Deep Research" is an AI agent skill, created by ClawHub Skill. ClawSecure audited "Deep Research" across 5 files through the 3-Layer Audit Protocol covering all ten OWASP ASI Top 10 categories, assigning a security score of 95/100 (Safe). The 3 findings concentrate in Policy Violation and Permissions Manifest, including Missing config.json - agent may not be properly configured and Skill name 'Deep Research' is invalid. Agent skills require…. None were rated high or critical severity.

Is "Deep Research" safe?

ClawSecure audited "Deep Research" and assigned a security score of 95/100 (Safe), identifying 3 findings across Policy Violation and Permissions Manifest. Review the findings below before installing.

What did ClawSecure find in "Deep Research"?

ClawSecure identified 3 findings in "Deep Research", concentrated in Policy Violation and Permissions Manifest. The most severe include Missing config.json - agent may not be properly configured and Skill name 'Deep Research' is invalid. Agent skills require….

How was "Deep Research" audited?

ClawSecure ran "Deep Research" through its 3-Layer Audit Protocol with full OWASP ASI Top 10 coverage, scanning 5 files.

What does a score of 95 mean?

ClawSecure assigned "Deep Research" a security score of 95/100, placing it in the Safe range. Scores of 80 or above qualify for ClawSecure Verified status; the 3 findings detected are lower-severity. 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 "Deep Research"

ClawSecure detected 3 security findings in "Deep Research", spanning Policy Violation and Permissions Manifest.

Each finding is expandable in the interactive list below.

3-Layer Audit Protocol

Security Recommendations for "Deep Research"

Resolve policy violations
"Deep Research" trips ClawSecure policy checks. Review each flagged pattern against your security policy and remediate or document an accepted exception before production use.
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→How to Secure an MCP Server: The 2026 Guide→

Related AI Agent Security Audits

sparkbtcbot-skillScore 90/100clippyScore 90/100stock-market-apiScore 95/100gtsec-smart-stock-selection (1)Score 95/100gtsec-smart-stock-selectionScore 95/100

Scanned on March 27, 2026. "Deep Research" 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