Overview
- Skill Key
- fermionoid/senseguard
- Author
- fermionoid
- Source Repo
- openclaw/skills
- Version
- -
- Source Path
- skills/fermionoid/senseguard
- Latest Commit SHA
- d5ec6280380f8daeeb9b5faa49656f8907884e01
Official OpenClaw
rules
36%
senseguard
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.
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
安装方式
直接复制以下提示词，发送给你的 AI 助手即可完成安装。
请先检查是否已安装 SkillHub 商店，若未安装，请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店，然后安装 senseguard 技能。 若已安装，则直接安装 senseguard 技能。
Extracted Content
SKILL.md excerpt
# 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.
Related Claw Skills
edholofy
dojo.md
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 required.
lethehades
wps-macos-helper
macOS WPS Office workflow helper skill for safer document preparation, conversion, export, and compatibility guidance
capt-marbles
firecrawl
Web scraping and crawling with Firecrawl API. Fetch webpage content as markdown, take screenshots, extract structured data, search the web, and crawl documentation sites. Use when the user needs to scrape a URL, get current web info, capture a screenshot, extract specific data from pages, or crawl docs for a framework/library.
caqlayan
Tweet Processor
Tweet Processor Skill
carev01
md-docs-search
Full-text search across structured Markdown documentation archives using SQLite FTS5. Use when you need to search large collections of Markdown articles that are separated by "---" delimiters and contain source URLs (marked with "*Source:" pattern). Provides fast BM25-ranked search with automatic source URL extraction for citations. Ideal for research, documentation lookups, and knowledge base exploration. Requires indexing documentation first with `docs.py index`.
camelsprout
duckdb-en
DuckDB CLI specialist for SQL analysis, data processing and file conversion. Use for SQL queries, CSV/Parquet/JSON analysis, database queries, or data conversion. Triggers on "duckdb", "sql", "query", "data analysis", "parquet", "convert data".