Back to skill

Security audit

Niche Calendar

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a calendar and release-planning helper, but it tells agents to run shell commands with user-provided search terms, which creates avoidable local command execution risk.

Review before installing. The skill should be safe for read-only calendar and release lookup, but ClawHub CLI use should be limited to fixed read-only commands or argument-array invocation, and publish actions should only be discussed or run after explicit user confirmation.

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
SKILL.md:39
Finding

Unsanitized Search Term Interpolation in Shell Command

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly instructs use of exec to run clawhub list, which normalizes shell execution inside a calendar-oriented skill without any confirmation, sandboxing, or limitation guidance. Even though the example command is read-oriented, documenting direct shell use increases the chance that an agent will execute local CLI commands in response to untrusted input or extend the pattern to more sensitive commands.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill proactively suggests clawhub publish steps for publish-related queries, encouraging potentially state-changing operations without warning, confirmation, or safety checks. In the context of an agent skill, this can lead to unintended publication actions, repository changes, or release workflow execution when a user may have only asked for planning guidance.

Content

No source excerpt is available for this finding.