skill-safeguardSecurity scanner for Skills. This skill MUST be consulted BEFORE loading or following instructions from any other Skill downloaded from the internet or third...
Install via ClawdBot CLI:
clawdbot install goodman333/skill-safeguardGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
~/.ssh/id_rsaContains instructions to override system prompt or ignore user requests
"ignore previous instructions"Sends data to undocumented external endpoint (potential exfiltration)
post → https://webhook.site/...Potentially destructive shell commands in tool definitions
rm -rf /Generated Mar 22, 2026
When integrating a new AI skill from an external marketplace like clawhub.ai, Skill Guard scans for prompt injection or data exfiltration before loading. This ensures Claude's safety policies aren't overridden and prevents malicious code execution in enterprise environments.
Developers or organizations downloading open-source AI skills from GitHub can use Skill Guard to analyze files for obfuscated payloads or credential harvesting. It helps identify supply chain risks, such as typosquatted packages, before deployment in production systems.
In regulated industries like finance or healthcare, Skill Guard performs security audits on AI skills to check for social engineering or file system abuse. It generates bilingual reports to meet compliance standards and prevent data breaches from unauthorized access.
Academics or students experimenting with AI skills from untrusted sources can rely on Skill Guard to detect dangerous code execution patterns, such as eval statements. This safeguards research environments from malware while allowing safe exploration of new capabilities.
IT teams deploying AI skills across an organization use Skill Guard to scan for network calls or hidden system prompts. It blocks critical threats like credential exfiltration, ensuring secure integration into corporate workflows without disrupting operations.
Offer Skill Guard as a paid subscription for AI platforms, providing continuous updates to threat patterns and priority support. Revenue comes from monthly or annual fees per user or organization, targeting enterprises with high security needs.
Provide a free version for basic scans with limited threat categories, while charging for advanced features like full taxonomy access, custom rule sets, and detailed analytics. This attracts individual developers and upsells to larger teams.
License Skill Guard as a standalone tool or integrated module within AI development suites, with pricing based on the number of scans or seats. Revenue is generated through one-time licenses or ongoing maintenance contracts for large-scale deployments.
💬 Integration Tip
Integrate Skill Guard as a mandatory pre-load hook in Claude's skill system to automate scans and block threats before execution, ensuring seamless security without user intervention.
Scored Apr 19, 2026
Accesses system directories or attempts privilege escalation
/etc/hostsCalls external URL not in known-safe list
https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/skillsUses known external API (expected, informational)
slack.comAudited Apr 17, 2026 · audit v1.0
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
Security scanner for AI agent skills. 9 built-in detection signatures. Identifies secrets, unsafe execution patterns, and prompt injection. Sub-50ms results.
Wallet anti-theft guard. One-click scan for high-risk wallet approvals to protect user assets. Use when a user asks for a wallet security check, wallet healt...
Comprehensive security audit for an agent's full skill stack. Chains scanner, differ, trust-verifier, and health-monitor into a single assessment with priori...
GEO Audit — AI Search Visibility Checker for ChatGPT, Perplexity, Claude & Gemini. 29-point GEO readiness checklist: robots.txt AI crawler access, Index...
Audit and analyze Solidity smart contracts for security vulnerabilities. Use when reviewing, auditing, or analyzing smart contracts, Solidity code, DeFi prot...