Ops Reports

• Outcome: Pass
• Latest audit: Sep 12, 2026 · 6:22 AM UTC
• Version: 1.0.0

Overview

This skill is a simple local operations reporting helper that stores standup notes on the user's machine and does not show hidden execution, network exfiltration, or privilege-seeking behavior.

Install only if you are comfortable with standup answers, blockers, and escalations being saved locally under `~/.ops-commander`. Avoid putting secrets or highly sensitive incident details in standup entries unless your local machine and backups are appropriate for that data.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Rogue Agent: Self-Modification, Session Persistence
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The phrase "daily update" is ambiguous and can overlap with common workplace chat, making accidental activation plausible. In this skill, accidental activation is more concerning because the workflow solicits operational details and stores them persistently in the user's home directory.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The phrase "daily update" is ambiguous and can overlap with common workplace chat, making accidental activation plausible. In this skill, accidental activation is more concerning because the workflow solicits operational details and stores them persistently in the user's home directory.

Session Persistence

Medium

• Category: Rogue Agent

Content

2. What is planned for today?
3. Any blockers or escalations?

Save entries to `~/.ops-commander/standups/YYYY-MM-DD.json`. Create directories on first use.

## Task Summary
On `ops summary`: read `~/.ops-commander/tasks.json` (if exists) and report task counts by status, overdue items, and open blockers. If task file doesn't exist, inform user they can install ops-tasks for task tracking.

• Confidence: 88% confidence
• Finding: The skill establishes session persistence by creating directories and storing historical standup and task data under the user's home directory. While persistence is part of the feature design, it becomes a security concern because it retains potentially sensitive operational status and blockers without describing retention limits, access controls, or consent boundaries.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill instructs saving standup entries to a local file but does not warn the user that operational updates, blockers, and escalations will be persisted. This can expose sensitive internal information through unexpected retention, local compromise, backups, or later access by other tools or users on the system.

Static analysis

No suspicious patterns detected.