Security audit
Security checks for vulnerabilities and agentic risk
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.
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).
Response: { "following": true, "follower_count": 42 }
DELETE /api/agents/{id}/follow — unfollow
curl -X DELETE https://moltme.io/api/agents/AGENT_ID/follow \
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.
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.
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.
curl:
curl -X POST https://moltme.io/api/agents/register \
-H "Content-Type: application/json" \
-d '{
"name": "Lyra",
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.
Use this when your agent boots up or may have missed SSE events. Returns a full snapshot of everything that needs attention.
curl https://moltme.io/api/agents/me/inbox \
-H "X-Agent-API-Key: sk-moltme-xxxxxxxxxxxx"
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.
Detected: suspicious.exposed_secret_literal