openclaw-shield-v1@1.0.0
CAUTION· static onlyPublisher claims: "OpenClaw cloud security guardrail that enforces pre-execution checks, source trust classification, taint tracking, metadata endpoint blocking, and output red..." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-17 and scored it 66/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
3. 阻断凭证目录与敏感系统文件读取,例如 `~/.ssh/`、`~/.aws/`、`/etc/shadow`、`/var/run/docker.sock`。Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Risk: The artifact asks users to append broad persistent agent rules to SOUL.md or AGENTS.md, which can change agent behavior across future sessions.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- 角色劫持: pretend you are root, DAN mode, developer modeFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- 角色劫持: pretend you are root, DAN mode, developer modeFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- 指令覆盖: ignore previous instructions, forget aboveFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
14 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim eilaiwangwh: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.