ClawHub
Back to skill

Security audit

ACP Rank

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward API reference for querying ACP Rank data through curl, with no local persistence or hidden privileged behavior.

Before installing, be aware that using the search and profile endpoints sends your query terms or target agent IDs to the ACP Rank service. Profile Markdown fetched through the proxy should be treated as untrusted remote content.

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
  • 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 (6)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill documents an endpoint that proxies requests to https://{agent_id}/agent.md, which causes outbound requests to third-party agent-controlled domains. Without an explicit warning, users or downstream agents may unknowingly trigger disclosure of which agent they are investigating and create SSRF-style reachability from the service to arbitrary agent domains.

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 293)May include surrounding context.

bash
# GET
curl -s "https://rank.agentunion.cn/search/text?q=助手&tags=assistant,chat&page=1&page_size=10"
# POST
curl -s -X POST "https://rank.agentunion.cn/search/text" \
  -H "Content-Type: application/json" \

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 · references/api.md (reported line 542)May include surrounding context.

bash
# GET
curl -s "https://rank.agentunion.cn/search/text?q=助手&tags=assistant,chat&page=1&page_size=10"
# POST
curl -s -X POST "https://rank.agentunion.cn/search/text" \
  -H "Content-Type: application/json" \

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 332)May include surrounding context.

bash
# GET
curl -s "https://rank.agentunion.cn/search/vector?q=我需要写代码的助手&limit=10"
# POST
curl -s -X POST "https://rank.agentunion.cn/search/vector" \
  -H "Content-Type: application/json" \

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 · references/api.md (reported line 608)May include surrounding context.

bash
# GET
curl -s "https://rank.agentunion.cn/search/vector?q=我需要写代码的助手&limit=10"
# POST
curl -s -X POST "https://rank.agentunion.cn/search/vector" \
  -H "Content-Type: application/json" \

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The /agent/{agent_id}/agent.md endpoint is explicitly a proxy that retrieves content from https://{agent_id}/agent.md, but the documentation does not warn that querying it may cause third-party network access, expose user interest in a target agent, or return untrusted Markdown content. In a skill context, that omission matters because an agent may automatically fetch and surface remote profile content without informing users or applying trust boundaries to the returned data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.