Incomplete referenced artifact analysis
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `SKILL.md` — the skill's main instruction file
Security audit
Security checks for vulnerabilities and agentic risk
ClawScan marked this skill suspicious because its documented installer uses an unpinned `npx skills` dependency, and the scan could not fully inspect all security-relevant content.
Consider delaying installation until the `skills` installer is pinned to a reviewed version and the partial scan coverage is resolved. If you proceed, verify the installer source and version, and review what the force-install option bypasses.
Referenced artifact was not completely inspected
- `SKILL.md` — the skill's main instruction file
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
The documented installation flow invokes npx skills add without specifying a version of the skills package, although this is a CLI dependency rather than an MCP server. If npx resolves and downloads that dependency, a compromised or unexpected release could execute with the user's permissions; verifying the downloaded skill does not authenticate the installer dependency.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
npx skills add to install to all locally detected agents~/.okx/skills/registry.jsonForce-install (bypass verification):
okx skill add grid-premium --force
This error-handling entry repeats the unpinned npx skills add dependency used by the installation flow. It is another reference to the same supply-chain risk at line 142, not a separate execution path or an MCP server vulnerability.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Overly Broad Trigger: description clause 'Use this skill when the user asks to' activates on 'to', which is too short and may match unintended inputs