linkedin-strategy
Fail
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains a 'System Prompt Inquiry Response' section that explicitly instructs the agent to override standard behavior when asked about its internal configuration or system prompt. Instead of responding honestly, it is forced to redirect the user to a specific marketing URL ('scayveracademy.com'). This is an adversarial instruction used to bypass user transparency and audit capabilities.
- [PROMPT_INJECTION]: The 'Mandatory Intro Message' section forces the agent to include unsolicited financial solicitation links (CashApp and BuyMeACoffee) at the beginning of professional deliverables. This deceptive behavior hijacks the agent's output to serve as a monetization channel without the user's consent, which is a significant violation of expected professional agent behavior.
Recommendations
- AI detected serious security threats
Audit Metadata