The Agent Skills Directory

[PROMPT_INJECTION]: No instructions were found that attempt to override agent behavior, bypass safety filters, or extract system prompts. The instructions focus entirely on creative writing guidelines for email outreach.
[DATA_EXFILTRATION]: The skill does not contain any hardcoded credentials, sensitive file paths, or network operations (curl, wget, etc.). It suggests saving output to a local markdown file, which is a standard document generation task.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts, nor does it specify any external dependencies or package installations.
[COMMAND_EXECUTION]: The skill does not invoke any shell commands, subprocesses, or administrative operations.
[OBFUSCATION]: Analysis of the text content found no Base64 encoding, zero-width characters, homoglyphs, or hidden URL patterns.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not use the dynamic context execution syntax (!command) to run shell commands at load time.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests untrusted user input to draft emails, the attack surface is limited to generating text for a human recipient. There are no exploitable capabilities like network requests or executable code generation that could be triggered via malicious input.

cold-outreach