Back to skill

Security audit

Diagnose Ollama Calls

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious with medium confidence because it references an unpinned `npx llmxray` package that could change between runs; the scan is also incomplete because one local reference was missing.

Consider the package supply-chain risk before installing: an unpinned `npx` command may run a different release later. The scan covered the listed component but was marked partial because a local reference could not be resolved, so the evidence is incomplete.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

MCP server referenced without pinned version: 'npx llmxray'.

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The unversioned npx llmxray command can download and execute a changing npm release with the user's privileges. A compromised future release could access local files and intercept the model traffic deliberately routed through this service; the skill's local-only and read-only claims do not constrain package execution.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

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.

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

md
| `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

MCP server referenced without pinned version: 'npx llmxray'.

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The troubleshooting instruction repeats the unpinned package-execution path, so restarting the service can resolve to an unreviewed npm release. This is the same supply-chain weakness as the setup command, with elevated consequences because the service receives the user's model requests.

Content

No source excerpt is available for this finding.