ClawHub
Back to skill

Security audit

Pushover

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Pushover connector, but it under-labels credential-revealing and credential-persisting actions as safe direct reads.

Review this skill before installing if your Pushover account has team administration, license, or production notification privileges. Treat token-related actions as sensitive and require explicit confirmation before revealing or storing credentials. Prefer inspecting or verifying the oo CLI installer rather than running the one-line remote install blindly.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs users to install software via a remote script piped directly into bash, which executes code fetched over the network without prior inspection or integrity verification. If the distribution endpoint, CDN, DNS, or transport path is compromised, this becomes an immediate arbitrary code execution path on the user's machine.

Content

Scanner excerpt · SKILL.md (reported line 83)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The instruction to use this skill for ANY Pushover request is overly broad and encourages routing all Pushover-related tasks through a single powerful connector, including destructive or credential-sensitive actions. In an agent setting, broad trigger scope increases the chance of accidental invocation in contexts where narrower, task-specific handling or additional confirmation would be safer.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The safety section says untagged actions are reads and safe to run directly, but the action list includes untagged operations like get_app_token, get_team_api_token, and store_team_api_token that expose or persist sensitive credentials rather than performing harmless reads. This can cause an agent to execute secret-revealing or secret-storing operations without confirmation, increasing the risk of credential disclosure or unauthorized state changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.