architect-interrogator
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions for the AI agent. There are no scripts, binaries, or external dependencies included.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied text to perform its 'interrogation' function, it lacks any high-risk capabilities (such as file system writes, network operations, or shell execution) that would make it vulnerable to indirect injection attacks.
- [DATA_EXFILTRATION]: There are no network requests or commands that could be used to send data to external servers.
- [COMMAND_EXECUTION]: The skill does not invoke any shell commands or subprocesses.
Audit Metadata