ClawHub
Back to skill

Security audit

Limehouse Calendar

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent calendar API skill with expected credentialed calendar access, including event deletion, but users should handle the token and delete permission carefully.

Install only if you trust cal.limehouse.io with the calendar data you grant. Give the API key the narrowest calendar permissions needed, avoid granting delete access unless required, and confirm event details before any delete operation. Treat CAL_API_KEY and returned agent_token values like passwords.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
94% confidence
Finding

The documented delete endpoint allows an agent to perform irreversible state-changing actions using attacker-influenced parameters such as calendar_id and event_id, without any built-in safety guidance. In a prompt-injection or user-confusion scenario, this could be abused to delete arbitrary accessible events from permitted calendars.

Content

Scanner excerpt · SKILL.md (reported line 234)May include surrounding context.

Delete an event

text
DELETE /api/v1/agent/calendars/{calendar_id}/events/{event_id}

Delete an event from a calendar. Requires can_delete. Returns 204 No Content.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The documentation tells the agent to authenticate with a bearer token and describes obtaining/storing an agent token, but it does not warn that the token is a sensitive secret that must not be logged, echoed, or exposed to users. If mishandled, the token grants calendar access within its scope and could allow unauthorized reading or modification of events.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill exposes a destructive DELETE operation for calendar events but does not instruct the agent to obtain explicit user confirmation before deletion. In an agent setting, this increases the risk of accidental or prompt-induced destructive actions that cannot be easily undone.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 364)May include surrounding context.

md
BASE="https://cal.limehouse.io/api/v1"

# Discover accessible calendars
curl -H "Authorization: Bearer $KEY" "$BASE/agent/calendars"

# List events for calendar 3 in January 2024
curl -H "Authorization: Bearer $KEY" \

Static analysis

No suspicious patterns detected.