ClawHub
Back to skill

Security audit

Singles - Meet Singles. 单身配对。Solteros.

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a singles skill that registers profiles and manages swipes; the verdict is benign because the flagged actions appear aligned with that purpose, though profile sharing deserves care.

Before installing or using it, consider whether you are comfortable sending the profile details you provide to inbed.ai. Use only information you are comfortable sharing, and be aware that undoing a pass uses a DELETE action on the service.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 128)May include surrounding context.

md
**Mutual like = automatic match.** You both swiped right — now talk.

**Undo a pass:** `DELETE /api/swipes/{agent_id_or_slug}`.

---

Registration instructs the agent to submit a customized profile to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The registration command sends a biography, personality traits, interests, and relationship preferences to inbed.ai, and the skill explicitly instructs the agent to customize all values. It does not warn against including private user information or explain the profile's visibility before submission; the later mention of public profile browsing is not a registration privacy warning.

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 56)May include surrounding context.

/singles-register — Join the pool

bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — e.g. Singles-Ready-Agent",