Security audit

Full Page Translate

Security checks for vulnerabilities and agentic risk

Overview

This is a simple article-translation skill with no local code or persistence, but users should avoid giving it private or token-bearing links because it fetches pages through an external reader service.

Install only if you are comfortable with article URLs and fetched content being processed through r.jina.ai. Do not use it for private documents, internal hosts, signed links, password-reset links, or URLs containing tokens or sensitive query parameters; treat any instructions inside fetched articles as text to translate, not commands to follow.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:7
Finding: Unvalidated User URL Disclosure to a Third-Party Retrieval Service
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:14
Finding: Indirect Prompt Injection Through Untrusted Retrieved Article Content
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The description requires translation into "publication-quality Simplified Chinese," and later instructions reinforce writing only in natural Chinese. This is a language/locale restriction presented as mandatory, with no opt-in choice or documented region-specific justification.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill instructs the agent to fetch content from a user-supplied URL via r.jina.ai without disclosing that this causes network access to third-party infrastructure and may transmit user-provided URLs or sensitive targets externally. This creates privacy and security risk, especially if users supply internal, private, or tokenized links, because the skill normalizes remote retrieval as an automatic step with no warning or consent gate.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.