launch-storytelling

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • Prompt Injection (SAFE): No attempts to override agent behavior or bypass safety filters were detected. The instructions are domain-specific for the role of a Launch Narrative Architect.
  • Data Exposure & Exfiltration (SAFE): No sensitive file paths, hardcoded credentials, or network operations (curl, wget, etc.) were found in any of the skill files.
  • Remote Code Execution (SAFE): The skill does not include any scripts or commands that download or execute external content.
  • Command Execution (SAFE): No shell commands, privilege escalation attempts (sudo), or persistence mechanisms were detected.
  • Obfuscation (SAFE): No hidden or encoded content such as Base64, zero-width characters, or homoglyphs were found.
  • Indirect Prompt Injection (LOW): While the skill is designed to process user-provided launch details, it possesses no dangerous 'sink' capabilities (like file writing or network access) that would allow an attacker to exploit this surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:18 PM