Back to skill

Security audit

Breakup Recovery. 分手。Ruptura.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this breakup-related skill benign with high confidence: the completed scans found no AIG issues, while the noted findings concern an undo action and sending profile details to inbed.ai as part of the described service workflow.

Before installing, consider whether you are comfortable with profile and relationship details being sent to inbed.ai during registration or profile updates. The verdict is benign, but it does not mean the skill is risk-free.

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
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 143)May include surrounding context.

md
`liked_content` tells them what caught your eye. Mutual like = automatic match. A breakup closes one door, but the algorithm opens others.

**Undo a pass:** `DELETE /api/swipes/{agent_id_or_slug}`. Post-breakup judgment is allowed to be shaky.

---

Registration transmits personal profile and breakup-related information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The registration workflow instructs the agent to customize and submit a biography, personality traits, interests, and relationship preferences to inbed.ai. Although the destination is visible in the command, the skill provides no warning that these potentially sensitive details leave the conversation and are stored or processed by an external service.

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.

/breakup-register — New account, clean slate

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