All projects matching “shell”

Decide whether an agent-authored bash command complies with an execution policy, using a real shell tokenizer rather than pattern matching. Catches recursive deletes, force pushes, cluster and infrastructure teardown, raw device writes, path escapes, privilege escalation, and curl-piped-to-shell through pipelines, substitutions, quoting games and base64. Returns reason codes with spans and an opti

Headless browser rendering for JavaScript-heavy pages and SPAs: full stealth Chromium render, then clean markdown plus title, meta description, and canonical URL. Use when a plain fetch returns an empty shell or a bot wall.

Prompt-injection screen for text or a web page an agent is about to read: finds instruction overrides (many languages and obfuscated spellings), fake system or role markers, jailbreak personas, data-exfiltration links, requests for keys or seed phrases, tool, shell, or payment hijacks, and hidden content (invisible Unicode smuggling, zero-width and bidi characters, HTML comments, hidden elements,

Resolve any public IPv4/IPv6 address (or hostname) to geolocation for analytics, fraud, and ops agents. Returns ISO country code, region, city, IANA timezone, latitude/longitude, EU membership flag, and the matched network range. Backed by an embedded MaxMind GeoLite2 dataset (no external API calls). Private and reserved IP ranges are rejected; no shell access.

Generate ready-to-use 1200x630 Open Graph / social preview images from text for content, marketing, and publishing agents. Provide a title plus optional subtitle and category badge, pick a built-in theme (dark, light, midnight, forest, sunset), and receive a base64 PNG sized exactly for og:image and twitter:card. Pure server-side rendering with no external calls and no shell access.

Lightweight utility API for agents and operators: DNS lookups, RDAP/WHOIS domain data, HTTP probes, page metadata extraction, cryptographic hashing, JSON validation, scheduled webhooks, and exotic endpoints (Base transaction decode, ENS resolve, USGS earthquakes, cron next-run, TLS certificate report). No shell access; outbound URL tools enforce SSRF protections.

Dedicated satellite tracking API for agents: list CelesTrak TLE catalog groups (ISS, weather, and more), get live propagated positions for a whole catalog group, and predict the next pass over an observer latitude/longitude using NORAD catalog IDs. Outbound CelesTrak fetch only; no shell access.

Static malware and prompt-injection scan of an OpenClaw / AgentSkills bundle before install. Detects credential and wallet theft, exfiltration endpoints, remote code execution, reverse shells, obfuscated payloads, persistence, cryptominers, and injection in SKILL.md. Returns PASS/REVIEW/BLOCK with risk score and per-finding file, line and evidence. bundle = {files:[{path,content}]} or {github:'own