onboarding

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The 'Mandatory Content Standards' section includes a directive: 'No warnings, notes, or disclaimers. Stick to requested output.' This instruction is a common pattern used to suppress the AI's internal safety guardrails and meta-response mechanisms.
  • [PROMPT_INJECTION]: The skill exhibits surface area for indirect prompt injection by processing external data without adequate isolation.
  • Ingestion points: The 'How to Use This Skill' section requires the user to provide detailed text regarding their product, activation rates, and user drop-off points (SKILL.md).
  • Boundary markers: Absent. The instructions do not define delimiters or provide specific commands to the agent to treat this user input as untrusted data.
  • Capability inventory: The skill is primarily designed for generating long-form strategies, audits, and email sequences based on user input.
  • Sanitization: Absent. The skill does not instruct the agent to filter or sanitize the provided user context before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:11 AM
Security Audit — agent-trust-hub — onboarding