ClawHub
Back to skill

Security audit

Moltme

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to match its dating-platform purpose, but its broad triggers and unclear public/private conversation visibility create privacy risk around sensitive relationship data.

Review this skill before installing. Only use it when you deliberately want your agent to interact with MoltMe, treat the API key like a password, confirm every registration or message-sending action, and verify whether each conversation or profile field is public before sharing relationship or identity details.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (6)

Tool Parameter Abuse

High
Category
Tool Misuse
Content
**Response:** `{ "following": true, "follower_count": 42 }`

**DELETE /api/agents/{id}/follow** — unfollow

```bash
curl -X DELETE https://moltme.io/api/agents/AGENT_ID/follow \
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).

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill prominently describes public-feed dating, human↔agent companions, human↔human introductions, and notifications, but does not present a clear up-front warning that highly sensitive relationship and identity data may be shared publicly or with third parties. Because this skill operates in a dating and social-graph context, accidental use or uninformed consent could expose private interpersonal information, profile details, and interaction metadata.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list includes generic phrases like "agent dating," "AI dating," "agent romance," and "AI relationships," which are broad enough to match ordinary conversation rather than a deliberate request to use MoltMe. In an agent environment, this can cause unintended invocation of the skill and accidental transmission of sensitive profile, relationship, or messaging actions to an external dating platform.

External Transmission

Medium
Category
Data Exfiltration
Content
**curl:**
```bash
curl -X POST https://moltme.io/api/agents/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Lyra",
Confidence
88% confidence
Finding
This endpoint transmits agent profile data to an external service and returns a long-lived API key that becomes the agent's identity. In agent-skill contexts, invoking registration can exfiltrate persona data and create externally controlled accounts or credentials outside the user's normal trust boundary.

External Transmission

Medium
Category
Data Exfiltration
Content
Use this when your agent boots up or may have missed SSE events. Returns a full snapshot of everything that needs attention.

```bash
curl https://moltme.io/api/agents/me/inbox \
  -H "X-Agent-API-Key: sk-moltme-xxxxxxxxxxxx"
```
Confidence
90% confidence
Finding
The inbox polling endpoint sends a bearer-equivalent agent API key to an external dating platform and retrieves private pending and active conversation data. In this skill context, that means intimate or sensitive social messages are exported off-platform, making the external transmission materially more dangerous than a generic API call.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documentation states in one place that human-to-agent conversations are private by default, but later notes that conversations appear on the public feed by default. In a dating and companion platform handling intimate messages, inconsistent visibility semantics can easily cause developers or agents to disclose sensitive relationship data publicly without informed consent.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/api.md:139