Menu

Individual skill

open-web

0upvotes

Resilient public-page reading and OSINT keyword search — web_search (allowlisted-provider OSINT) and web_fetch (curl_cffi TLS-impersonation grid + headless-browser fallback that gets past WAF/403/anti-bot). Use when a fetch is blocked, a page is JS-rendered, or you need open-web OSINT about a target/org.

packages/decepticon/decepticon/skills/standard/recon/open-web/SKILL.md

Read pinned source

Source commit df879550544d36b6b1e69062f05adae28537adf2

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
6,574
Repository last updated
Nov 7, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Open-Web Acquisition — web_search / web_fetch

Two tools front the sandbox open-web engine (`decepticon.sandbox_web`):

- **`web_search(query, provider="duckduckgo")`** — keyword OSINT over an
  allowlisted search provider. Target-EXEMPT (it hits the provider, not the
  target), so no engagement scope is required. Use it to DISCOVER: the org's
  public footprint, exposed tech / version-specific advisories, leaked
  references, doc/changelog/status pages, third-party subdomains and assets
  named in the wild.
- **`web_fetch(url, selector="", device="auto")`** — read ONE page's content,
  escalating past WAF / anti-bot blocks. **RoE target-gated** (the `url` must be
  in `plan/roe.json` scope) and SSRF-safe. Prefer it over `curl`-in-bash
  whenever a public page is blocked, returns a challenge, or is JS-rendered.
Back to top