Security audit

Ai Paper Survey

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent AI literature-survey skill with expected search, read, analysis, and report-writing behavior, with only minor user-control cautions.

Before installing, be aware that the skill may read matching keyword files from the current working directory and will create a report file there. Use it in workspaces where those research-interest files are intended for the assistant, and check the generated filename if overwrite behavior matters.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The description includes broad trigger phrases like 'do a literature review' and 'find what's new,' which are common user requests and may cause the skill to activate in situations where the user did not intend to invoke this specific workflow. Because the skill performs multi-step searches, reads files, and writes output, accidental activation can lead to unnecessary tool use and unintended file access or report generation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The 'When to Use' section lists generic example prompts such as 'What's new in ... research?' and 'Do a literature review on [topic],' which are ambiguous and overlap with many normal assistant tasks. In an agentic environment, this can over-broaden routing and cause the skill to run with tools when a plain conversational response would have been sufficient.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill description is broad enough to match many ordinary research requests, which can cause the agent to invoke this skill in situations the user did not explicitly intend. Because the skill reads local files, performs external searches, and writes a report to disk, overbroad triggering increases the chance of unnecessary data access and side effects.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The 'When to Use' examples are phrased as common conversational requests without guardrails, making accidental invocation more likely. In this skill, mistaken activation is more significant because the workflow includes scanning the working directory for keyword files, contacting external tools, and generating output files.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill instructs the agent to save a Markdown report into the working directory without any explicit user-facing disclosure or confirmation at the point of action. While the write is not inherently dangerous, silent file creation can surprise users, overwrite expectations about workspace state, and combine with accidental invocation to create unintended artifacts.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The skill instructs the agent to save a Markdown report to disk without requiring user confirmation or warning that a file will be created. This can lead to unexpected filesystem side effects, accidental overwrite conflicts, or persistence of sensitive research topics in shared workspaces.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.