ClawHub

Site Profile

v1.0.0

Short alias for external-site-profile-learning. Use this when investigating, adding, validating, or debugging external website profiles for the 99idea Playwr...

⭐ 0· 38·0 current·0 all-time
by@allens0104
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (site profiling for Playwright/Gemini flows) matches the instructions. Nothing in the skill requests unrelated permissions, binaries, or credentials.
✓
Instruction Scope
SKILL.md tells the agent to probe sites, classify UI patterns, create data-only profiles, and run validation commands — all consistent with site-profile tasks. The instructions do not ask the agent to read local files, environment variables, or send data to unexpected external endpoints.
✓
Install Mechanism
No install spec and no code files are present (instruction-only). This minimizes disk writes and arbitrary code execution risk.
✓
Credentials
The skill requires no environment variables, credentials, or config paths. That aligns with an instruction-only profiling helper which operates by browsing/testing external sites.
✓
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent/forced inclusion or modify other skills. Autonomous invocation is allowed by default but is not combined with other high-risk factors here.
Assessment
This is an instruction-only helper for creating and validating Playwright/Gemini site profiles and appears internally consistent. Before using: be aware that 'probing' will cause the agent to visit external sites (so avoid placing secrets or credentials in prompts), review the referenced full playbook (skills/external-site-profile-learning/SKILL.md) if available, and run validations in a sandbox or with rate limits if you worry about heavy or popup-heavy sites. If you plan to integrate this into automated runs, confirm what the validate:external:* commands do in your environment (they may trigger many requests).

Like a lobster shell, security has layers — review code before you run it.

latestvk974kmrq8mqwabzgexv8nj42s18453qv

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments