Back to skill

Security audit

Fuxux Social Manager

Security checks for vulnerabilities and agentic risk

Overview

The skill clearly discloses its social media management permissions and provides reasonable controls for posting and deletion.

Connect only accounts you want managed, protect the API key, and use drafts to review content before publishing. Uploaded media becomes publicly accessible. Prefer direct HTTP MCP or a reviewed, pinned bridge version.

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

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · .clawhubignore (reported line 1)May include surrounding context.

text
.env
.env.*
*.zip
.DS_Store

MCP Config Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · README.md (reported line 10)May include surrounding context.

md
| File | Purpose |
|------|---------|
| **[SKILL.md](./SKILL.md)** | Agent instructions + ClawHub YAML frontmatter (`metadata.openclaw`) — the only file ClawHub requires |
| **[examples/openclaw-mcp.json](./examples/openclaw-mcp.json)** | Copy-paste MCP config (`mcp-remote` + Bearer token) |

## Quick start (users)

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 289)May include surrounding context.

8. Delete a scheduled post

http
DELETE /api/posts/{post_id}

Works with your fx_live_ API key. A draft or scheduled post is removed and will never publish. For an already-published post this deletes only Fuxux's record — it does not remove the post from the social platform. Returns 409 while the post is mid-publish; wait a moment and retry.

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 415)May include surrounding context.

md
| `POST /api/media/upload` | ✅ |
| `GET /api/posts/{id}` | ✅ |
| `PATCH /api/posts/{id}` | ✅ |
| `DELETE /api/posts/{id}` | ✅ |
| `POST /api/ai/generate` | ✅ |

When a route returns `401` with an API key, tell the user to complete the action in the Fuxux web app or use MCP tools that wrap supported routes.

MCP server referenced without pinned version: 'npx envVars'.

Medium
Category
MCP Rug Pull
Confidence
96% confidence
Finding

Although the matched line merely lists npx as a prerequisite, the same source installs mcp-remote without a version and provides an npx -y mcp-remote launch configuration. This allows an unreviewed package release to execute with the agent host's privileges and access the supplied bearer token, potentially compromising connected social accounts if the dependency is compromised.

Content

No source excerpt is available for this finding.