outreach
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists exclusively of markdown instructions and message templates. It does not include any scripts, binaries, or configuration files that could be executed on a host system.
- [DATA_EXFILTRATION]: The skill does not utilize network-connected tools such as curl or wget. It operates solely on the input provided by the user (research briefs and prospect data) and does not attempt to access sensitive local system files like credentials or SSH keys.
- [PROMPT_INJECTION]: While the skill contains strong negative constraints (e.g., 'NEVER DO THESE'), these are alignment instructions designed to prevent the AI from generating poor-quality or unethical sales content. There are no attempts to bypass safety filters or override the agent's core identity.
- [REMOTE_CODE_EXECUTION]: No package managers (pip, npm) or remote script execution patterns were found. The skill does not download external content for runtime execution.
Audit Metadata