ClawHub
Back to skill

Security audit

Super Freedcamp Agent Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Freedcamp integration, with expected live project-management write access and local session caching that users should understand before enabling.

Install this only if you want an agent to read and modify your Freedcamp workspace. Use the least-privileged Freedcamp credentials available, confirm before create/update/comment/mark-read actions, and restrict access to the local session cache or set FREEDCAMP_SESSION_PATH to a protected location.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill exposes multiple state-changing operations such as creating and updating tasks, posting comments, and marking notifications as read, but it does not prominently warn users or agents that these actions modify remote project data. In an agent context, missing write-operation warnings increases the chance of unintended actions, especially because the skill is user-invocable and mixes read and write commands in the same documentation without explicit confirmation guidance.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill persists sensitive session material, including the Freedcamp API session token and user ID, to a predictable path under the user's home directory without any permission hardening, encryption, or user disclosure. If another local process, user, backup system, or log collection mechanism can read that file, the token may be reused to access the user's Freedcamp account and data until it expires or is revoked.

Static analysis

Detected: suspicious.env_credential_access, suspicious.potential_exfiltration

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/freedcamp.mjs:22

Sensitive-looking file read is paired with a network send.

Warn
Code
suspicious.potential_exfiltration
Location
scripts/freedcamp.mjs:180