ClawHub
Back to skill

Security audit

Claw Calendar

Security checks for vulnerabilities and agentic risk

Overview

This calendar skill is coherent and not deceptive, but it gives an assistant API-key authority to update and delete calendar data without clear confirmation safeguards.

Review this skill before installing. It appears to do what it claims, but only use it with a calendar API key you are comfortable allowing to create, update, and delete calendar data. Prefer a limited-scope key if available, and confirm exact event or calendar details before allowing delete actions.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
91% confidence
Finding

The skill includes a direct DELETE endpoint for calendar events with no documented confirmation, preview, or ambiguity-handling safeguards. Because the skill is driven by natural language and uses privileged API credentials, a misinterpreted request or prompt-influenced invocation could lead to unauthorized or unintended deletion of user data.

Content

Scanner excerpt · SKILL.md (reported line 87)May include surrounding context.

Delete Event

text
DELETE /api/calendars/{calendarId}/events/{eventId}
Headers: X-API-Key: ${CALENDAR_API_KEY}

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/api_reference.md (reported line 97)May include surrounding context.

Delete Calendar

text
DELETE /api/calendars/{calendarId}
Headers:
  X-API-Key: ${CALENDAR_API_KEY}

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/api_reference.md (reported line 198)May include surrounding context.

Delete Event

text
DELETE /api/calendars/{calendarId}/events/{eventId}
Headers:
  X-API-Key: ${CALENDAR_API_KEY}

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger description is broad enough that an assistant may invoke the skill for many ordinary calendar-related requests without strong confirmation boundaries. In a skill that can create, update, and delete events using stored credentials, over-broad activation increases the chance of unintended actions on a user's calendar.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The documentation exposes destructive delete functionality but does not warn that it can permanently remove calendar events or recommend confirmation before execution. In the context of a natural-language skill, this omission makes accidental or ambiguous destructive actions more likely, especially when the assistant interprets user intent imperfectly.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file documents DELETE operations for calendars without any warning about irreversible or data-affecting behavior. Under the markdown-specific missing-warning rule, descriptions of behaviors that can affect user data should disclose the risk so users understand the consequence before invoking the skill or API.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file describes deleting events and notes that deleted event data is returned, but it does not clearly warn that the action changes user data and may be destructive. For markdown files, operations affecting user data should include an explicit caution so the user is aware of the impact.

Content

No source excerpt is available for this finding.