poke-holes-in-this
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely composed of natural language instructions and output templates. It does not contain any scripts, command-line executions, or system calls.
- [SAFE]: There are no indicators of data exfiltration, obfuscation, or persistence mechanisms. The skill does not request or use any sensitive file paths or network tools.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process arbitrary user-provided text ('The thing'). While this text is an ingestion point for untrusted data, the skill lacks any capabilities (such as file-writing, network access, or tool execution) that could be abused via prompt injection. The risk is limited to the text-to-text response generation.
Audit Metadata