The Agent Skills Directory

[PROMPT_INJECTION]: No evidence of malicious instructions, jailbreak attempts, or safety filter bypasses were found. The skill uses standard instructional language to define formatting and content guidelines.
[DATA_EXFILTRATION]: No network requests, external URLs, or sensitive file path references (such as SSH keys or environment variables) were detected.
[REMOTE_CODE_EXECUTION]: The skill does not perform any external downloads, script executions, or package installations. It is a purely text-based instructional prompt.
[COMMAND_EXECUTION]: No shell commands, subprocess calls, or privilege escalation attempts (like sudo) are present.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided context about investors and companies, it lacks the functional capabilities (like tool usage, file writing, or network access) that would make it vulnerable to exploitation. There is no risk of data exfiltration or unintended actions.
[SAFE]: The skill's behavior is consistent with its stated purpose of assisting with fundraising outreach.

investor-outreach