ClawHub
Back to skill

Security audit

Super Freedcamp Agent Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a real Freedcamp automation skill, but it caches reusable session credentials insecurely and exposes broad live-write capabilities that need review before installation.

Install only if you are comfortable giving the skill access to your Freedcamp workspace and allowing it to create or modify tasks, comments, and notification state. Avoid running the demo in a workspace with a shared .env file, restrict the Freedcamp API credentials to the minimum needed account, treat the local session cache as sensitive, and remove cached credentials when no longer needed.

A.I.G

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (3)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/freedcamp.mjs:176
Finding

Plaintext Session Cache Created Without Explicitly Restrictive Permissions

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
scripts/demo.mjs:17
Finding

Demo Loads Unrelated Secrets from a Parent Workspace Environment File

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
README.md:45
Finding

Setup Documentation Encourages Printing Stored API Credentials

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (11)

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 · scripts/demo.mjs (reported line 7)May include surrounding context.

js
*
 * Usage:  node skill/scripts/demo.mjs
 *
 * Loads .env from project root automatically if env vars aren't set.
 */

import { execFileSync } from "node:child_process";

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 · scripts/demo.mjs (reported line 20)May include surrounding context.

js
*
 * Usage:  node skill/scripts/demo.mjs
 *
 * Loads .env from project root automatically if env vars aren't set.
 */

import { execFileSync } from "node:child_process";

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 · scripts/demo.mjs (reported line 23)May include surrounding context.

js
// Load .env if needed
function loadEnv() {
  if (process.env.FREEDCAMP_API_KEY && process.env.FREEDCAMP_API_SECRET) return;
  const envFile = path.join(ROOT, ".env");
  if (!fs.existsSync(envFile)) return;
  for (const line of fs.readFileSync(envFile, "utf-8").split("\n")) {
    const match = line.match(/^(?:export\s+)?(\w+)=(.+)$/);

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 · README.md (reported line 94)May include surrounding context.

node scripts/freedcamp.mjs task <task_id>

text

### 5) Create a task

```bash
node scripts/freedcamp.mjs create-task --project <project_id> --title "New task"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README prominently documents commands that create tasks, update tasks, add comments, and mark notifications as read, but it does not clearly warn that these operations affect live Freedcamp data. In an agent-tooling context, users or agents may treat examples as safe exploratory commands, increasing the chance of unintended writes to production workspaces.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill requires environment secrets and makes network calls, but it does not declare an explicit tool scope such as allowed-tools or permissions. That creates an authorization gap where an agent or reviewer cannot easily constrain what capabilities the skill is expected to use, increasing the chance of unintended secret access or outbound requests beyond user expectations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill documents multiple state-changing operations such as creating tasks, updating tasks, adding comments, and marking notifications as read without an explicit warning or confirmation boundary. In an agent setting, this increases the risk of unintended remote modifications to production project data from ambiguous prompts or automation mistakes.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill is presented as project-management automation, but the documentation enables commenting across broader app domains including CRM, Passwords, Files, Wikis, and Calendar. This widens the reachable data surface and could let an agent modify or inject content into sensitive or unrelated areas, especially the Passwords app, beyond what a user may reasonably expect from the skill description.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description says the skill can create, update, and organize tasks, projects, groups, comments, notifications, and task lists. In the implementation, projects and groups are only enumerated via session data, and task lists are only listed; no commands create, update, or reorganize those resource types.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The manifest describes project-management automation against Freedcamp's API, but this demo additionally reads arbitrary environment-style secrets from a local .env file and injects them into process.env. While this may be convenient for local testing, local credential-file access is not part of the stated business purpose and is an extra capability beyond interacting with Freedcamp itself.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The code can add comments, fetch notifications, and mark notifications read, but it does not implement general create/update/organize behavior for notifications or task lists as implied by the manifest's broad wording. This is a semantic overstatement of skill behavior rather than an implementation detail.

Content

No source excerpt is available for this finding.