Security audit

Jina Reader

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it sends URLs or search queries to Jina AI to fetch readable page content or search results.

Install only if you are comfortable sending requested URLs, search terms, and any configured JINA_API_KEY to Jina AI services. Avoid using it with private internal URLs, URLs containing tokens, sensitive personal data, or confidential research queries unless that third-party processing is acceptable.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (7)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 94% confidence
Finding: The skill advertises search capability and broad search-related triggers, but the provided implementation details appear centered on URL reading and may not fully implement the promised behavior. This mismatch is dangerous because users and orchestration logic may invoke the skill under incorrect assumptions, potentially causing unintended network requests, silent failures, or routing of user data to third-party services without clear expectation.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: The skill advertises search capability and broad search-related triggers, but the provided implementation details appear centered on URL reading and may not fully implement the promised behavior. This mismatch is dangerous because users and orchestration logic may invoke the skill under incorrect assumptions, potentially causing unintended network requests, silent failures, or routing of user data to third-party services without clear expectation.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill clearly documents use of network access and optional environment-variable based API keys, but it does not declare any tool scope such as allowed-tools or permissions. That omission weakens governance and review controls, making it harder to constrain what the skill is permitted to access and increasing the chance of unintended network or secret exposure in execution environments.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are broad enough to overlap with many ordinary requests such as summarization, lookup, or content retrieval. Over-broad activation can cause the skill to run unexpectedly, sending user-provided URLs or queries to external services and expanding the attack surface for prompt routing abuse or unintentional data disclosure.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The documentation does not clearly warn users that supplied URLs and search queries are transmitted to third-party Jina endpoints. This is dangerous because users may unknowingly send sensitive internal links, tokens embedded in URLs, private search terms, or regulated data to an external processor, creating confidentiality and compliance risks.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: This script sends a user-supplied URL to a third-party service endpoint (r.jina.ai) and may also attach a bearer token from the environment. That creates a real privacy and security concern because sensitive URLs, internal resource locations, query parameters, or authenticated access patterns could be disclosed externally without any explicit warning, validation, or restriction.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The script sends the full user-supplied search query to an external third-party service at s.jina.ai, and there is no user-facing notice, consent flow, or redaction of potentially sensitive input before transmission. This creates a real privacy and data-handling risk because users may provide secrets, internal URLs, personal data, or proprietary research terms that are then disclosed outside the local environment.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.