ClawHub
Back to skill

Security audit

Idea Coach

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent idea manager that stores notes locally and uses user-triggered GitHub commands, with no artifact-backed evidence of hidden or malicious behavior.

Before installing, treat stored idea content as local plaintext data and review it before syncing to GitHub, especially when using public repositories or issue creation. Use the GitHub commands only when you intend to let the skill act through your authenticated gh account.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (16)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 126)May include surrounding context.

md
python scripts/coach.py add "Build something cool" --type idea --importance important

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 129)May include surrounding context.

md
python scripts/coach.py add "Build something cool" --type idea --importance important

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

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

md
python scripts/coach.py add "Build something cool" --type idea --importance important

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 131)May include surrounding context.

md
python scripts/coach.py add "Build something cool" --type idea --importance important

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 134)May include surrounding context.

md
python scripts/coach.py add "Build something cool" --type idea --importance important

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 135)May include surrounding context.

md
python scripts/coach.py add "Build something cool" --type idea --importance important

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 136)May include surrounding context.

md
python scripts/coach.py add "Build something cool" --type idea --importance important

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 137)May include surrounding context.

md
python scripts/coach.py add "Build something cool" --type idea --importance important

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The concept includes automated morning checks, overdue nudges, and weekly summaries, but it does not specify any explicit user consent flow, disclosure, or easy opt-out before ongoing reminders are sent. This creates a privacy and user-safety risk because the system may retain behavioral data and initiate outreach unexpectedly, potentially exposing sensitive personal project information or causing unwanted notifications.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The technical design documents persistent local storage, per-entry interaction logs, cron-based automation, and memory integration across conversations without a corresponding privacy notice, consent model, retention policy, or access controls. Because the stored content includes ideas, problems, challenges, and progress history, this can expose sensitive personal or work-related information and enable broader profiling across sessions.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · README.md (reported line 41)May include surrounding context.

md
brew install gh
  
  # Linux
  sudo apt install gh
  
  # Then authenticate
  gh auth login

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill describes capabilities that read/write local files and invoke shell-based workflows (python scripts/coach.py ..., gh CLI) but does not declare any explicit tool scope or permissions boundary. That omission increases the chance an agent or user enables the skill without understanding its local-system and command-execution reach, which can lead to unintended file modification or command execution in a higher-privilege environment.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The GitHub integration advertises actions that create repositories and sync issues to a remote service, including optional public repo creation, but it does not clearly warn that idea contents may be transmitted off-device or become publicly visible. In this skill's context, users may store sensitive project ideas or internal problem statements, so silent or poorly signposted publication/synchronization creates a meaningful confidentiality risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill's natural-language logic classifies all content as either German or English based on simple heuristics, with no user opt-in or way to select another language. This creates a locale policy issue because language behavior is forced implicitly rather than offered as a user choice or documented as a region-specific limitation.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/coach.py (reported line 275)May include surrounding context.

python
def run_gh_command(args: List[str]) -> Dict[str, Any]:
    """Run a gh CLI command and return result."""
    try:
        result = subprocess.run(
            ["gh"] + args,
            capture_output=True,
            text=True,

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The markdown describes that ideas are stored in ~/.openclaw/idea-coach/ideas.json, but it does not provide a user-facing warning that the skill persists potentially sensitive idea content to disk. Because this file may contain private plans or problem statements, the description should clearly disclose local data retention behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.