Markdown Browser

Wrapper skill for OpenClaw web_fetch results. Use when you need MECE post-processing on fetched pages: policy decision from Content-Signal, privacy redaction...

This skill appears coherent and limited in scope: it processes an existing web_fetch JSON, normalizes text, computes a simple policy decision from a Content-Signal header, and redacts URL parts. Things to consider before installing: (1) npm install will fetch the 'turndown' package from the public registry—audit that dependency if you need supply-chain assurance; (2) redaction is heuristic: query values are replaced with '[redacted]' for parameter names that match a short sensitive list and '[masked]' otherwise—this may not catch all secrets, so don’t rely on it as a perfect sanitizer; (3) the policy decision logic is simple (ai-input yes/no/other -> allow/block/needs_review) and depends on correctly-formed headers; malformed headers may yield 'needs_review'; (4) the skill does not make network requests itself, but it will output whatever is in the supplied web_fetch_result, so ensure the source of that JSON is trusted. Overall the skill is internally consistent with its stated purpose.

Type: OpenClaw Skill Name: markdown-browser-skills-openclaw Version: 0.1.0 The skill is designed to post-process `web_fetch` results, applying policy decisions, privacy redaction, and content normalization. The `SKILL.md` explicitly instructs the agent to use OpenClaw's `web_fetch` and not to perform direct HTTP fetches, which is a positive security indicator. The `browser.js` code implements the stated functionality, including a robust URL redaction feature for privacy. File system access is limited to reading input data (from stdin or a specified file path) for processing, which is a legitimate use case for a CLI utility. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts with harmful intent.