Academic Paper Parse

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 5:30 AM UTC
• Version: 1.2.0

Overview

This skill performs disclosed academic-paper reading and report generation, with limited temporary file handling that fits its purpose.

Install this if you want structured academic paper reports. Provide only papers or URLs you are comfortable having processed, and remember that URL-based papers may need to be fetched externally while the skill creates a final markdown report in the workspace.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The invocation description is broad enough to activate on generic requests for analysis, close reading, interpretation, or summarization, even when the user has not clearly asked to process an academic paper PDF or URL. That can cause unintended skill routing and trigger file handling or network-retrieval behavior in contexts where the user expected a normal chat response, increasing the chance of over-collection or unnecessary external access.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The workflow explicitly instructs the agent to download URL-sourced PDFs, but it does not require informing the user that external network access will occur or obtaining consent first. This can surprise users, expose request metadata to third parties, and enable retrieval from untrusted or tracking-controlled URLs.

Missing User Warnings

Low

• Confidence: 88% confidence
• Finding: The markdown instructs using the file tool's delete action to remove `temp_analysis.md`, which is a destructive operation. Although cleanup is minor and limited to a temporary file, the skill description does not explicitly warn users that it will create and then delete a local file during execution.

Natural-Language Policy Violations

Low

• Confidence: 89% confidence
• Finding: The file is a natural-language writing template entirely phrased as mandatory English output guidance, including instructions to follow the structure strictly. Because the policy scope includes language or locale constraints across all file types, this can be read as enforcing English without an explicit user choice or opt-in.

Static analysis

No suspicious patterns detected.