Back to skill

Security audit

Claw Calendar Skill

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it says, but its configurable API endpoint can receive the user's calendar API key despite documentation saying the key only goes to the official service.

Install only if you trust the Claw Calendar service and can protect the API key. Do not set CLAW_CALENDAR_API_URL unless it is a trusted HTTPS endpoint, because the scripts will send the API key and calendar data there. Treat created events, reminders, and subscription URLs as external account changes that may sync to devices.

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

Error
Location
scripts/create-calendar.js:6
Finding

Unrestricted API endpoint configuration can disclose the Bearer credential and calendar data

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (11)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 50)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 90)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 93)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

The code sends authenticated requests to a remote endpoint using a bearer token from an environment variable, yet static analysis indicates network capability is undeclared. In a skill ecosystem, undeclared network egress is dangerous because it can enable data exfiltration or unauthorized external communication outside the permissions users and reviewers expect.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
97% confidence
Finding

The code sends authenticated requests to a remote endpoint using a bearer token from an environment variable, yet static analysis indicates network capability is undeclared. In a skill ecosystem, undeclared network egress is dangerous because it can enable data exfiltration or unauthorized external communication outside the permissions users and reviewers expect.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The markdown explicitly tells users to export CLAW_CALENDAR_API_KEY, but it does not warn that this value is a secret credential that should be protected and not committed, logged, or shared. Because this file is a markdown skill description, omission of a privacy/security warning around credential handling fits the missing user warnings category.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill documents commands that create calendars, add events, and enable reminders, but it does not clearly warn that these actions modify external calendar data and may propagate to connected devices through subscription/sync behavior. This can cause unintended writes, reminders, and data exposure across a user's phone or desktop calendars if the user or agent invokes the skill without explicit awareness of those side effects.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This JavaScript file contains natural-language comments and error/output strings exclusively in Chinese, including usage guidance and failure messages. Under the policy rule for language/locale, this is a violation because the skill does not offer user opt-in or document that it is intentionally limited to a Chinese-speaking or region-specific context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script explicitly formats dates with the 'zh-CN' locale and all user-facing messages are in Chinese, which imposes a specific language/locale on users. Under the policy, this is a natural-language locale violation unless the skill offers user opt-in or clearly documents a justified region-specific constraint.

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 user-facing natural-language text entirely in Chinese, including the top-level usage description and runtime messages. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and 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

The code hard-codes the locale 'zh-CN' for date formatting, which forces a specific language/locale in user-visible output. The file does not offer an opt-in, fallback, or configuration mechanism, and no region-specific justification is documented here.

Content

No source excerpt is available for this finding.