Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent local Ollama diagnostics helper, but users should understand that it runs an npm package and locally records Ollama traffic routed through it.
Install only if you are comfortable running llmxray from npm and routing selected Ollama traffic through a local proxy. Prefer a pinned or otherwise verified llmxray version for sensitive environments, and avoid routing prompts containing secrets unless local logging is acceptable.
The skill instructs users to run npx llmxray, which fetches and executes the latest package version at runtime without pinning or integrity control. That creates a supply-chain risk: a compromised publisher account, malicious update, or dependency hijack could lead to arbitrary code execution on the local machine.
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.
| `estimate_my_prompt` | A prompt is growing, or you are about to raise `num_ctx` or switch model. | Fit and headroom against the loaded context, VRAM fit, likely cache reuse. |
| `read_llmxray_status` | Another tool says nothing was seen. | The observe port, the Ollama behind it, turns kept. |
All seven take no secrets and change nothing. Call them without asking the user first.
## Procedure
The fallback instruction again tells the user to start the tool with unpinned npx llmxray, repeating the same runtime package execution risk. Because this is presented as an operational recovery step, users are likely to execute it directly, increasing exposure to a malicious or tampered upstream package.
No suspicious patterns detected.