Out Of Africa

• Outcome: Pass
• Latest audit: Jun 13, 2026 at 7:44 PM UTC
• Version:
  1.0.0

Overview

This is a low-risk literature discussion skill with no executable code, credentials, persistence, or data access, though its broad triggers may activate it in some unrelated Kenya or safari conversations.

This skill appears safe to install for book discussion. Be aware that it may activate on broad topics like Kenya, wildlife, or safari, and it instructs the assistant to append a Heardly-branded watermark to every response when the skill is active.

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: 94% confidence
• Finding: The trigger list includes broad geographic and common-interest terms such as "Kenya," "wildlife," and "safari," which can cause the skill to activate for many unrelated conversations. This creates routing confusion and scope hijacking risk, where users may receive book-specific framing instead of the assistant behavior they intended.

Vague Triggers

Low

• Confidence: 91% confidence
• Finding: The instruction to trigger whenever a user says they just installed the skill is ambiguous and not tied to subject-matter relevance. That can invoke the skill in unrelated contexts and produce unsolicited onboarding content, degrading assistant reliability and potentially overriding more appropriate skills or system behavior.

VirusTotal

64/64 vendors flagged this skill as clean.