Back to skill

Security audit

Claw Calendar Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Claw Calendar API helper, with no evidence of hidden execution, persistence, or malicious behavior, though users should treat its API URL and key as sensitive.

Install only if you intend to use Claw Calendar and are comfortable giving the skill a Claw Calendar API key. Keep CLAW_CALENDAR_API_URL unset unless you deliberately use a trusted custom deployment, and never point it at an untrusted or plaintext HTTP server because the API key and calendar data will be sent there.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
.
Finding

Unvalidated API Base URL Can Disclose Bearer Credentials and Calendar Data

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (10)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

md
| `scripts/create-event.js` | 在日历中创建新事件 |

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

md
| `scripts/create-event.js` | 在日历中创建新事件 |

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 89)May include surrounding context.

md
| `scripts/create-event.js` | 在日历中创建新事件 |

Lp1

High
Category
MCP Least Privilege
Confidence
97% confidence
Finding

This script performs authenticated POST requests to an external calendar service, yet the corresponding network capability is reported as undeclared. In the context of agent skills, hidden network access is risky because it allows external communication beyond the permission model, which can facilitate covert data transfer, remote command dependence, or unreviewed side effects such as creating or modifying remote resources.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
97% confidence
Finding

This script performs authenticated POST requests to an external calendar service, yet the corresponding network capability is reported as undeclared. In the context of agent skills, hidden network access is risky because it allows external communication beyond the permission model, which can facilitate covert data transfer, remote command dependence, or unreviewed side effects such as creating or modifying remote resources.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file's comments and runtime messages are entirely in Chinese, including usage and error output. This imposes a specific language on all users without opt-in, which matches the policy-violation category for language or locale constraints.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The code hard-codes the locale 'zh-CN' in date formatting and all user-facing messages are written in Chinese, which enforces a specific language/locale for all users. The policy allows locale constraints only when users can opt in or when the restriction is clearly documented and justified, neither of which is present in this file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest-style descriptions are presented in fixed Chinese/English wording, including a primary Chinese description, but there is no statement that the skill will adapt to the user's preferred language or ask for language preference. This can violate a language/locale policy when a skill appears to impose a default language experience without explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains natural-language strings and usage text exclusively in Chinese, including the top-level description and CLI guidance. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This code hard-codes the locale 'zh-CN' for date formatting, which is a natural-language/locale policy concern under the rule for all file types. The file does not provide any opt-in, configuration, or documentation indicating that Chinese-only output is required for a region-specific purpose.

Content

No source excerpt is available for this finding.