ClawHub
Back to skill

Security audit

Calendly

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for Calendly automation, but it includes an unverified remote installer that an agent may run if the required CLI is missing.

Install only if you trust OOMOL and are comfortable using its CLI to manage Calendly data. Prefer installing the oo CLI from a verified, documented release path instead of allowing an agent to run the provided curl/PowerShell one-liners, and require explicit confirmation before any Calendly write or delete action.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (3)

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 · SKILL.md (reported line 50)May include surrounding context.

md
- `delete_invitee_no_show` — Delete one Calendly invitee no-show by no-show URI. [destructive]
- `delete_organization_membership` — Delete one Calendly organization membership by membership URI. [destructive]
- `delete_webhook_subscription` — Delete one Calendly webhook subscription by URI. [destructive]
- `get_current_user` — Retrieve the authenticated Calendly user for the connected personal access token.
- `get_event_invitee` — Retrieve one Calendly invitee by invitee URI.
- `get_event_type` — Retrieve one Calendly event type by event type URI.
- `get_invitee_no_show` — Retrieve one Calendly invitee no-show by no-show URI.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs users to install software by piping a remotely fetched script directly into a shell, which is a high-risk supply-chain and remote-code-execution pattern. If the install endpoint, DNS, TLS trust, or distribution pipeline were compromised, arbitrary code could execute immediately on the host running the skill setup.

Content

Scanner excerpt · SKILL.md (reported line 91)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is configured as the handler for essentially any Calendly-related request, which gives it very broad authority over both read and write operations, including destructive actions. In an agent setting, this increases the chance of accidental invocation for ambiguous prompts and can route users into high-privilege workflows without sufficient narrowing or user-intent validation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.