每周安排助理

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:36 PM UTC
• Version:
  1.0.0

Overview

This is a local weekly planning skill that saves and summarizes planner data, with no evidence of hidden network access, credential use, or unrelated destructive behavior.

Install this only if you want a planner that stores your work plans, completion notes, and reflections in local ./weekly-plans JSON files. Avoid putting secrets or highly sensitive reflections there, and remember that deleting a plan is a soft delete, so some data may remain in the files until manually removed.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 94% confidence
• Finding: The skill performs persistent local file writes to ./weekly-plans and may also read prior records, but it does not declare permissions or clearly scope those capabilities. Hidden persistence increases the risk of unexpected data retention and unauthorized file access assumptions by the host or user, especially because the skill stores potentially sensitive work logs and reflections.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger conditions are broad enough to activate on generic requests about planning, summaries, or progress, which can cause the agent to invoke this skill unexpectedly. In context, unexpected invocation is risky because the skill persists user work data to disk and may transform ordinary conversation into stored records without deliberate consent.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill description and workflow do not prominently warn users that their plans, completions, and reflections are automatically persisted to local JSON files. This creates a privacy and consent issue because users may share sensitive work details assuming they are only generating a transient summary, while the skill silently retains them.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The manual trigger phrase includes 'or similar expressions' without defining boundaries, which can cause the agent to invoke the reporting workflow on ambiguous or unintended user inputs. In an agent setting, overly broad triggers increase the risk of unauthorized actions, privacy leakage from showing work-report data, or prompt-routing mistakes caused by natural-language ambiguity.

VirusTotal

66/66 vendors flagged this skill as clean.