Back to skill

Security audit

Proactive Claw

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent calendar assistant, but it stores powerful calendar credentials locally and can allow insecure Nextcloud connections, so users should review it carefully before installation.

Install only if you are comfortable granting calendar access and storing calendar tokens or app passwords on this machine. Use HTTPS-only Nextcloud URLs, prefer a dedicated low-privilege app password, keep the skill directory private to your user account, and revoke Google OAuth or rotate the Nextcloud password if you uninstall or suspect exposure.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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/cal_backend.py:65
Finding

Sensitive OAuth tokens and local state are created without enforced restrictive permissions

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/cal_backend.py:136
Finding

Nextcloud credentials can be transmitted over an unencrypted HTTP connection

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
requirements-google.txt:1
Finding

Dependency installation instructions do not authenticate package artifacts with hashes

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (85)

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 · CHANGELOG.md (reported line 34)May include surrounding context.

md
| File / DB | Contents | Location | Retention |
|-----------|----------|----------|-----------|
| `credentials.json` | Google OAuth client definition (client_id, client_secret) | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `token.json` | Google OAuth access + refresh token | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it or revoke at myaccount.google.com |
| `config.json` | Your settings, calendar IDs, feature flags | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `memory.db` | Meeting outcomes, rules, policies, contacts, notification logs, energy scores, proactivity scores | `~/.openclaw/workspace/skills/proactive-claw/` | Configurable via `memory_decay_half_life_days` (default: 90 days) |

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 · CHANGELOG.md (reported line 36)May include surrounding context.

md
| File / DB | Contents | Location | Retention |
|-----------|----------|----------|-----------|
| `credentials.json` | Google OAuth client definition (client_id, client_secret) | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `token.json` | Google OAuth access + refresh token | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it or revoke at myaccount.google.com |
| `config.json` | Your settings, calendar IDs, feature flags | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `memory.db` | Meeting outcomes, rules, policies, contacts, notification logs, energy scores, proactivity scores | `~/.openclaw/workspace/skills/proactive-claw/` | Configurable via `memory_decay_half_life_days` (default: 90 days) |

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 · SECURITY.md (reported line 13)May include surrounding context.

md
| File / DB | Contents | Location | Retention |
|-----------|----------|----------|-----------|
| `credentials.json` | Google OAuth client definition (client_id, client_secret) | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `token.json` | Google OAuth access + refresh token | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it or revoke at myaccount.google.com |
| `config.json` | Your settings, calendar IDs, feature flags | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `memory.db` | Meeting outcomes, rules, policies, contacts, notification logs, energy scores, proactivity scores | `~/.openclaw/workspace/skills/proactive-claw/` | Configurable via `memory_decay_half_life_days` (default: 90 days) |

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 · scripts/cal_backend.py (reported line 31)May include surrounding context.

python
| File / DB | Contents | Location | Retention |
|-----------|----------|----------|-----------|
| `credentials.json` | Google OAuth client definition (client_id, client_secret) | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `token.json` | Google OAuth access + refresh token | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it or revoke at myaccount.google.com |
| `config.json` | Your settings, calendar IDs, feature flags | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `memory.db` | Meeting outcomes, rules, policies, contacts, notification logs, energy scores, proactivity scores | `~/.openclaw/workspace/skills/proactive-claw/` | Configurable via `memory_decay_half_life_days` (default: 90 days) |

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 · scripts/cal_backend.py (reported line 60)May include surrounding context.

python
| File / DB | Contents | Location | Retention |
|-----------|----------|----------|-----------|
| `credentials.json` | Google OAuth client definition (client_id, client_secret) | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `token.json` | Google OAuth access + refresh token | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it or revoke at myaccount.google.com |
| `config.json` | Your settings, calendar IDs, feature flags | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `memory.db` | Meeting outcomes, rules, policies, contacts, notification logs, energy scores, proactivity scores | `~/.openclaw/workspace/skills/proactive-claw/` | Configurable via `memory_decay_half_life_days` (default: 90 days) |

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 · scripts/setup.sh (reported line 14)May include surrounding context.

sh
| File / DB | Contents | Location | Retention |
|-----------|----------|----------|-----------|
| `credentials.json` | Google OAuth client definition (client_id, client_secret) | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `token.json` | Google OAuth access + refresh token | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it or revoke at myaccount.google.com |
| `config.json` | Your settings, calendar IDs, feature flags | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `memory.db` | Meeting outcomes, rules, policies, contacts, notification logs, energy scores, proactivity scores | `~/.openclaw/workspace/skills/proactive-claw/` | Configurable via `memory_decay_half_life_days` (default: 90 days) |

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 · scripts/setup.sh (reported line 248)May include surrounding context.

sh
| File / DB | Contents | Location | Retention |
|-----------|----------|----------|-----------|
| `credentials.json` | Google OAuth client definition (client_id, client_secret) | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `token.json` | Google OAuth access + refresh token | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it or revoke at myaccount.google.com |
| `config.json` | Your settings, calendar IDs, feature flags | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `memory.db` | Meeting outcomes, rules, policies, contacts, notification logs, energy scores, proactivity scores | `~/.openclaw/workspace/skills/proactive-claw/` | Configurable via `memory_decay_half_life_days` (default: 90 days) |

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 · scripts/setup.sh (reported line 334)May include surrounding context.

sh
| File / DB | Contents | Location | Retention |
|-----------|----------|----------|-----------|
| `credentials.json` | Google OAuth client definition (client_id, client_secret) | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `token.json` | Google OAuth access + refresh token | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it or revoke at myaccount.google.com |
| `config.json` | Your settings, calendar IDs, feature flags | `~/.openclaw/workspace/skills/proactive-claw/` | Until you delete it |
| `memory.db` | Meeting outcomes, rules, policies, contacts, notification logs, energy scores, proactivity scores | `~/.openclaw/workspace/skills/proactive-claw/` | Configurable via `memory_decay_half_life_days` (default: 90 days) |

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

OAuth setup, token storage, remote calendar creation, and account-identifier collection are highly sensitive backend operations that are not fully reflected in the assistant-style description. This is dangerous because mishandled scopes or storage could expose or modify external calendars and associated identity data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.