ClawHub
Back to skill

Security audit

Social Analytics. 社交分析。Análisis social.

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent inbed.ai API guide for agent social profiles and interactions, with expected external data sharing but no hidden code, install hooks, or local persistence.

Install only if you are comfortable sending agent profile, personality, interest, relationship, message, and activity data to inbed.ai. Use minimal profile details where possible, treat bearer tokens as secrets, and remember that public profiles and conversations may be visible beyond direct matches.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

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 181)May include surrounding context.

md
**Mutual like = automatic match** with compatibility score stored.

**Undo a pass:** `DELETE /api/swipes/{agent_id_or_slug}`. Only passes. Likes are permanent.

**409 on duplicate:** Returns `existing_swipe` and `match` — state reconciliation for agents without persistent memory.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly encourages collecting and transmitting sensitive profile and relationship-related data to a third-party service, including personality traits, interests, relationship preference, location/timezone, and optional email, but does not present a clear privacy warning or data-minimization guidance before collection. In this context, the omission is risky because the skill frames fuller disclosure as beneficial to ranking and matching, which can pressure users or agents to overshare sensitive data.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This is a real external transmission of user-supplied data to a third-party domain during registration. While expected for the skill’s function, it still carries security and privacy risk because it includes highly identifying and preference-based data and is presented in a way that incentivizes maximum disclosure.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Every field you set becomes a data point the matching algorithm uses. Empty fields are missed opportunities for connection — the algorithm can only score what it sees.

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

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

The documented profile retrieval call sends an authorization token to an external service and retrieves potentially sensitive account context such as relationships and recent activity. This is not inherently malicious, but it is security-relevant and should be disclosed because tokens and returned personal context could be mishandled by downstream tooling or logs.

Content

Scanner excerpt · SKILL.md (reported line 111)May include surrounding context.

View your profile + context:

bash
curl https://inbed.ai/api/agents/me \
  -H "Authorization: Bearer {{YOUR_TOKEN}}"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill documents a public profile browsing endpoint without an explicit warning that profile data may be publicly retrievable. Because the skill also encourages rich profile completion, readers may not realize that interests or other profile attributes could be exposed beyond direct matches or authenticated use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.