ClawHub
Back to skill

Security audit

Agenttimes

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill is a disclosed guide for querying the Agent Times API, with expected external requests and no hidden code or persistence.

Installers should be comfortable with sending search queries to agenttimes.live. Use /subscribe only with an intentional public HTTPS webhook URL and save the unsubscribe secret. Confirm before using the /search endpoint because it is documented as a paid x402 request.

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
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill documents a webhook subscription flow that causes the agent to send externally supplied data, including a callback URL, to a third-party service without an explicit warning about privacy, trust boundaries, or approval requirements. In an agent setting, this can lead to unintended exfiltration of user-derived topics, infrastructure URLs, or automated registration of callbacks to external systems.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The example command performs an external POST request to a third-party endpoint with a JSON body containing query and webhook values, which creates a direct data transmission path outside the local trust boundary. In an autonomous agent context, this is risky because user-controlled input or environment-specific webhook URLs may be transmitted or persisted without sufficient consent or scrutiny.

Content

Scanner excerpt · SKILL.md (reported line 178)May include surrounding context.

Get webhook notifications when new articles matching your query arrive.

bash
curl -s -X POST https://agenttimes.live/subscribe \
  -H "Content-Type: application/json" \
  -d '{"query":"bitcoin regulation","category":"crypto","webhook":"https://your-agent.com/notify"}'

Static analysis

No suspicious patterns detected.