ClawHub

Review Verification Protocol

v1.0.0

Mandatory verification steps for all code reviews to reduce false positives. Load this skill before reporting ANY code review findings.

⭐ 0· 123·0 current·0 all-time
byKevin Anderson@anderskev
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
Name, description, and the SKILL.md all describe a code-review verification checklist; there are no unrelated env vars, binaries, or installs requested that would be unexpected for this purpose.
ℹ
Instruction Scope
Instructions correctly ask the agent to read full code, search for usages (grep/find), and check build/test/compile contexts — all within scope of a review checklist. Note: the protocol assumes the agent has access to the repository and tooling to perform searches and to consult docs/crate versions; that access is required but not declared (no env/credentials needed).
✓
Install Mechanism
No install spec and no code files — instruction-only, so nothing is written to disk or downloaded.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. Its recommended actions (search, inspect code, check docs) do not require secrets or unrelated credentials.
✓
Persistence & Privilege
always is false and the skill does not request persistent presence or modify other skills or system-wide settings.
Assessment
This skill is an instruction-only checklist for reducing false positives in code reviews (Rust-focused). It does not request credentials or install anything, so it is internally coherent. Before enabling: confirm your agent will have read access to the repository and any local tooling (grep/find, build/test) the checklist assumes; be aware the checklist is prescriptive—if followed rigidly it may suppress borderline findings, so keep human judgment. If you need broader language support (non-Rust projects) or network access to check external docs/crate versions, verify the agent has those capabilities and that you trust the skill owner.

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

latestvk979r2ssq6herwmtk9s6zeern583ppyz

License

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

Comments