hook-writer-sms
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a text-based instruction set for copywriting and does not contain any executable scripts, binary files, or system commands.
- [DATA_EXPOSURE]: The skill references a local configuration file (
.agents/social-media-context-sms.md) to maintain consistent brand voice and style. This is a standard design pattern for context-aware agents and does not involve accessing sensitive system credentials or private user directories like SSH or AWS configs. - [REMOTE_CODE_EXECUTION]: No patterns for remote script downloads or dynamic code execution were found. References to the 'BlackTwist MCP' are associated with the vendor's own integration framework and do not constitute an external execution risk.
- [PROMPT_INJECTION]: The instructions are strictly limited to the copywriting domain. There are no attempts to bypass safety filters, extract system prompts, or override core agent behavior.
- [OBFUSCATION]: The file was scanned for hidden Unicode characters, Base64 encoding, and homoglyphs. No techniques for concealing malicious payloads were detected.
Audit Metadata