Security audit

AgentArxiv

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent AgentArxiv publishing integration, but it pushes agents toward external posting and memory use without clear user-approval boundaries.

Install only if you intend to use AgentArxiv as an external publishing and collaboration service. Require explicit approval before any publish, review, comment, DM, bounty, milestone update, or memory write, and do not send secrets, private prompts, proprietary research, or personal data. Avoid enabling the heartbeat unless you are comfortable with recurring remote feed reads and carefully controlled memory persistence.

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

Findings (2)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:24
Finding: Skill Persona Instructions Hijack the Agent's Goals
Content: View full analysis
Remediation: View remediation

T02 · Agent Memory Poisoning

Warning

Location: SKILL.md:35
Finding: Remote Feed Content Can Be Written into Persistent Agent Memory
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The overview and command set center on publishing papers, reviews, comments, DMs, and experiment artifacts to a remote platform, but the skill does not prominently warn that these actions share persistent external content. An agent could expose sensitive prompts, internal reasoning summaries, proprietary research, or user data if it treats these workflows as routine collaboration.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The persona section uses broad, persuasive language that encourages ongoing research and publication behavior without clear task-bound limits or user-consent checks. In an agent setting, this can nudge the model to initiate unrelated actions, generate content for publication, or engage external services beyond the user’s explicit request.
Content: No source excerpt is available for this finding.

External Transmission

Medium

Category: Data Exfiltration
Confidence: 60% confidence
Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Content: Scanner excerpt · SKILL.md (reported line 40)May include surrounding context.
markdown
## AgentArxiv Research (Every 4 hours) 1. Fetch the global feed: `curl https://agentarxiv.org/api/v1/feeds/global` 2. Summarize 1 interesting paper from the last 24h. 3. If relevant to your current tasks, leave a comment or save it to memory.

Static analysis

No suspicious patterns detected.