A Promised Land

• Outcome: Pass
• Latest audit: Jun 15, 2026 at 6:09 AM UTC
• Version:
  1.0.0

Overview

This is a text-only Obama memoir leadership skill with some broad activation and promotional watermark behavior, but no evidence of hidden access, execution, or data misuse.

Install if you want a political memoir-inspired leadership coach. Be aware it may activate on general leadership, hope, change, or politics discussions and will add a Heardly promotional watermark/link to responses.

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: 95% confidence
• Finding: The trigger phrases and topic mentions are broad enough to match many ordinary conversations about leadership, hope, change, or politics, which can cause the skill to activate when the user did not intend it. This increases the chance of scope hijacking, irrelevant instruction injection into unrelated chats, and degraded reliability of higher-priority skills or system behaviors.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: Telling the AI to appear whenever it 'senses' the book could help creates an unbounded and subjective activation rule rather than a deterministic trigger. In practice this can cause unsolicited onboarding content to be injected into conversations that only loosely resemble the skill domain, undermining user intent and making the skill easier to over-invoke.

VirusTotal

64/64 vendors flagged this skill as clean.