ClawHub

Browser Site Profile

v1.0.0

Shortest English alias for site-profile / external-site-profile-learning. Use this when turning an already-proven site flow into a stable reusable external p...

⭐ 0· 41·0 current·0 all-time
by@allens0104
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The skill is presented as a short alias for 'site-profile' / 'external-site-profile-learning' and its SKILL.md contains only guidance about probing and turning a site flow into a reusable profile. There are no unrelated environment variables, binaries, or install steps requested.
ℹ
Instruction Scope
The runtime instructions are high-level ("probe the site", "classify the failure mode", "add a data-only profile", "validate flows"). They do not instruct reading local files, accessing credentials, or sending data to unexpected endpoints. However, the phrasing is broad and grants the agent discretion about how to 'probe' a site; the detailed playbook referenced (skills/external-site-profile-learning/SKILL.md) is not included here and could contain more concrete steps.
✓
Install Mechanism
No install spec and no code files are present. As an instruction-only skill, nothing is written to disk and no external packages or downloads are requested.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. There is nothing disproportionate requested for the described profiling task.
✓
Persistence & Privilege
always is false and there is no indication the skill modifies other skills or system-wide settings. It does not request permanent presence or elevated agent privileges.
Assessment
This skill is low-risk and coherent with its description, but it's intentionally high-level. Before enabling it, ask to see the referenced detailed playbook (skills/external-site-profile-learning/SKILL.md) to confirm what exact network calls or data storage it will perform. Do not supply credentials to the agent unless a later, explicit step asks for them and you verify why they're needed. Monitor the agent's actions when it first runs this skill (network access, saved profiles, or external endpoints) so you can revoke it if it starts collecting or transmitting site data you didn't expect.

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

latestvk978wnczy1pbkn46as43zj5cf1844d64

License

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

Comments