pm-experiment-designer
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses on statistical design and document generation without requesting dangerous permissions or tools.
- [PROMPT_INJECTION]: No patterns of instruction override, safety bypass, or system prompt extraction were found in the persona guidelines.
- [DATA_EXFILTRATION]: The skill does not access sensitive environment variables, credentials, or local configuration files, and lacks network capabilities.
- [REMOTE_CODE_EXECUTION]: There are no commands for installing third-party packages or executing remote scripts via the shell.
- [COMMAND_EXECUTION]: The skill does not use subprocesses or shell commands; its output is restricted to text and a local HTML asset.
- [SAFE]: While the skill ingests user experiment data, it lacks high-privilege capabilities (network, file-write, shell) that could be exploited by malicious data.
Audit Metadata