ClawHub
Back to skill

Security audit

Briefing (Calendar Agenda, Weather, Pending To-Dos)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed daily briefing orchestrator that reads calendar, todo, and weather data only for its stated purpose.

Install only if you are comfortable letting the agent read your configured calendar, active todos, and default-location weather for briefings. If you enable the suggested cron delivery, choose a private channel and verify the schedule, timezone, and permissions.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
For each available source, **read its `SKILL.md` before calling any commands**.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README explicitly states the skill is available for the agent to invoke when 'contextually appropriate', but it does not define clear guardrails for when autonomous invocation is allowed. Because this skill aggregates calendar, todo, and weather data and may also be scheduled for delivery, ambiguous auto-invocation can lead to unprompted access to sensitive personal information or unintended outbound delivery to chat channels.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description says the skill provides a daily briefing by gathering several sources, but it does not specify concrete trigger phrases, activation boundaries, or examples of when it should not be invoked. For a user-invocable markdown skill, this can create ambiguity about when ordinary requests for summaries or planning assistance might activate the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.