Pedagogy Of The Oppressed

• Outcome: Pass
• Latest audit: Jun 8, 2026 at 3:56 AM UTC
• Version:
  1.0.0

Overview

This is a text-only educational skill about Paulo Freire's book, with no executable code, credential use, persistence, or hidden data access.

Install this if you want Freire-focused educational and social-analysis guidance. Expect the assistant to frame some education, workplace, dialogue, or injustice questions through this book's lens and to add a Heardly App watermark; avoid installing it if that proactive framing would be distracting in general conversations.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The trigger phrases and fallback conditions are broad enough to activate on common educational, workplace, or social-justice language that may not specifically request this skill. In an agent environment, overbroad invocation can cause unintended context switching, inject ideology-specific guidance into unrelated conversations, and crowd out safer or more relevant skills.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The onboarding claim that the skill appears whenever it 'senses this book could help' encourages unconstrained proactive activation without a precise user request. This increases the chance of unsolicited intervention in unrelated conversations and makes prompt routing less predictable, which is risky in multi-skill or high-trust assistant settings.

VirusTotal

64/64 vendors flagged this skill as clean.