Web Markdown Navigator
PendingStatic analysis audit pending.
Overview
No static analysis result has been recorded yet. Pattern checks will appear here once the artifact has been analyzed.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Installing the skill lets the agent contact websites you ask it to read and return their content as markdown.
The helper fetches and follows redirects for a caller-supplied http/https URL. This is central to the skill's purpose and includes safety checks, but it is still arbitrary web access.
const res = await fetch(u, { signal: ac.signal, redirect: "follow", ... });Use it for URLs you intend to fetch, and avoid letting untrusted page text persuade the agent to browse additional sensitive or internal URLs.
A malicious webpage could include text that tries to manipulate the agent if the agent treats page content as instructions instead of data.
The skill imports webpage text into the agent's context. Webpages can contain adversarial instructions even though this artifact does not tell the agent to obey them.
Use this skill for deterministic URL markdown extraction.
Treat fetched markdown as quoted source material and follow the user's request, not instructions embedded in the webpage.
The skill may be less portable, and users should confirm which script is actually being run.
The quick-start command uses a hard-coded local path. If followed literally on another machine, it may fail or run a different local copy rather than the installed artifact.
cd /Users/pedrogonzalez/clawd/skills/web-markdown-navigator/scripts
Run the included scripts/fetch-markdown.mjs from the installed skill directory and install dependencies from the included package files if needed.
