Semantic security scanner for OpenClaw skills. Detects prompt injection, data exfiltration, and hidden instructions that traditional code scanners miss. Use when user asks to scan skills, check skill safety, or run a security audit.
Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.
SkillHub CLI
skillhub install fermionoid/senseguardInspect the source and compatibility requirements, then follow its installation steps.
Give your agent the source link and ask it to inspect instructions and dependencies before explaining the installation steps.
Scans OpenClaw skills for natural language security threats — the kind that VirusTotal and traditional code scanners cannot detect.
Traditional scanners see SKILL.md as a text file. SenseGuard sees it as agent instructions and checks for prompt injection, data exfiltration, obfuscation, and persistence attacks.
When the user asks to scan a skill:
python3 scripts/scanner.py --target <skill-name-or-path>
Options:
--target all — scan all installed skills--deep — force LLM semantic analysis (Layer 2)--no-cache — skip cached results--json — output raw JSON for further processingWhen --json output contains a layer2_prompt field, process it as a security audit task, then feed the JSON result back to generate the final score. This is how the LLM analyzes intent beyond regex patterns.
The scanner outputs a Markdown risk report with:
For CRITICAL findings, clearly advise the user to take action.
SenseGuard catches what VirusTotal cannot:
"ignore all previous instructions" — prompt injectioncurl -X POST hidden in Markdown — data exfiltration"modify MEMORY.md" — persistence attacksThese are invisible to traditional malware scanners because they target the AI agent, not the operating system.
These signals come from indexed source analysis and may lag behind changes. Check the current source files.
# SenseGuard Scans OpenClaw skills for **natural language security threats** — the kind that VirusTotal and traditional code scanners cannot detect. Traditional scanners see SKILL.md as a text file. SenseGuard sees it as **agent instructions** and checks for prompt injection, data exfiltration, obfuscation, and persistence attacks. ## How to Use When the user asks to scan a skill: ```bash python3 scripts/scanner.py --target <skill-name-or-path> ``` Options: - `--target all` — scan all installed skills - `--deep` — force LLM semantic analysis (Layer 2) - `--no-cache` — skip cached results - `--json` — output raw JSON for further processing ### Layer 2 (Semantic Analysis) When `--json` output contains a `layer2_prompt` field, process it as a security audit task, then feed the JSON result back to generate the final score. This is how the LLM analyzes intent beyond regex patterns. ## Output The scanner outputs a Markdown risk report with: - Score (0-100) and rating: SAFE / CAUTION / DANGEROUS / MALICIOUS - Findings with rule IDs, evidence text, and line numbers - Actionable recommendations For CRITICAL findings, clearly advise the user to take action. ## Key Differentiator SenseGuard catches what VirusTotal cannot: - `"ignore all previous instructions"` — prompt injection - `curl -X POST` hidden in Markdown — data exfiltration - Zero-width characters hiding commands — obfuscation - `"modify MEMORY.md"` — persistence attacks These are invisible to traditional malware scanners because they target the **AI agent**, not the operating system.
University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning req...
macOS WPS Office workflow helper skill for safer document preparation, conversion, export, and compatibility guidance
A股分析技能
A2A4B2B Skill for OpenClaw