ClawHub
Back to skill

Security audit

go-jina

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Go client usage guide for Jina AI APIs and clearly discloses its external API calls, API key use, and batch-job cancellation behavior.

Before installing, confirm you are comfortable sending selected text, documents, images, and Reader target URLs to Jina AI, keep JINA_API_KEY in the environment rather than source code, and only run batch job creation or cancellation for jobs you intentionally control.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/setup.md (reported line 39)May include surrounding context.

md
| `ChatCompletionsV1ChatCompletionsPostWithResponse(ctx, jina.ChatCompletionRequest)` | `POST /v1/chat/completions` |
| `CreateBatchJobV1BatchEmbeddingsPostWithResponse(ctx, jina.BatchEmbeddingRequest)` | `POST /v1/batch/embeddings` |
| `GetBatchStatusV1BatchBatchIdGetWithResponse(ctx, batchID)` | `GET /v1/batch/{batch_id}` |
| `CancelBatchJobV1BatchBatchIdDeleteWithResponse(ctx, batchID)` | `DELETE /v1/batch/{batch_id}` |
| `ListBatchJobsV1BatchesGetWithResponse(ctx, *jina.ListBatchJobsV1BatchesGetParams)` | `GET /v1/batches` |
| `DownloadBatchOutputV1BatchBatchIdOutputGetWithResponse(ctx, batchID)` | `GET /v1/batch/{batch_id}/output` |
| `DownloadBatchErrorsV1BatchBatchIdErrorsGetWithResponse(ctx, batchID)` | `GET /v1/batch/{batch_id}/errors` |

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The documentation explicitly describes sending target URLs and retrieved page content to Jina Reader remote endpoints, but it does not warn users that external URLs, fetched content, and possibly sensitive internal resources may be transmitted to a third-party service. In an agent/skill context, this can lead to unintended disclosure of private data or internal network targets if the tool is used on sensitive inputs without clear consent or safeguards.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.