to-prompt
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of markdown instructions without any associated scripts or configuration files. No malicious patterns, obfuscation, or hidden commands were detected.
- [PROMPT_INJECTION]: The instructional language, including the use of
<critical>tags and "MUST/MUST NOT" directives, is used appropriately to define the skill's operational logic. It does not attempt to override agent safety filters or system instructions. - [DATA_EXFILTRATION]: The skill does not perform network requests or attempt to access sensitive files such as credentials, environment variables, or SSH keys.
- [REMOTE_CODE_EXECUTION]: There are no commands related to package installation (npm, pip) or remote script execution (curl, wget).
Audit Metadata