awkward-message-helper
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of natural language instructions and prompt templates. It does not include any scripts, executables, or command-line operations.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-provided descriptions of personal situations and relationships. While these are untrusted inputs, the skill does not possess any dangerous capabilities (such as network access, file system writes, or subprocess execution) that could be exploited via prompt injection.
- [SAFE]: The functionality is restricted to providing drafting advice and message templates. No indicators of malicious behavior, obfuscation, or data exfiltration were detected.
Audit Metadata