ClawHub
Back to skill

Security audit

Frihet ERP

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documented, read-first Frihet ERP MCP operating contract with explicit user-controlled setup and no artifact-backed hidden credential access or persistence.

Install only if you intend to connect an agent to Frihet ERP. Keep the documented literal read-only allowlist in place before OAuth login, and opt into mutating tools only when you understand the Frihet workspace, scopes, and approval behavior in your host runtime.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

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

Content

Scanner excerpt · SKILL.md (reported line 176)May include surrounding context.

md
work around.

### 6. Credentials belong to the host
Frihet OAuth tokens, refresh tokens, and access tokens are managed by the
host agent. The Frihet plugin:

- NEVER reads `~/.hermes/mcp-tokens/*`

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 130)May include surrounding context.

md
## Operating doctrine

### 1. Read before write
Before any `create_*` / `update_*` / `mark_*_paid` / `delete_*`, re-read the
target record (or its absence) so the model — and the human — can verify
the operation is acting on the latest state. Caching is fine; guessing is

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 211)May include surrounding context.

text
# Does the Frihet MCP respond?
curl -fsS https://mcp.frihet.io/mcp -X POST -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{
        "protocolVersion":"2025-06-18",

Static analysis

No suspicious patterns detected.