Agent OKR

• Outcome: Pass
• Latest audit: Jun 18, 2026 at 4:17 AM UTC
• Version:
  1.0.0

Overview

The available signals show a coherent planning/reporting skill with a disclosed file-writing concern that users should review, but no evidence of malicious behavior.

Before installing, expect the skill to create or update local OKR/report YAML files and review diffs before committing them. Use it in a repository where those files are appropriate, and avoid treating generated planning data as authoritative without human review.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill explicitly describes an automated workflow that writes weekly report data into repository-tracked YAML files, but it does not clearly warn that using the skill will modify files in the repo. In an agent setting, silent or poorly disclosed file mutation can cause unintended commits, overwrite human edits, or create integrity issues in operational planning data, especially if triggered automatically on a schedule.

VirusTotal

63/63 vendors flagged this skill as clean.