product-manager-agent
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructional templates for transforming an AI agent into a Product Manager persona. All instructions are aligned with the stated purpose of product planning and requirement analysis.
- [SAFE]: No evidence of prompt injection, obfuscation, or unauthorized data exfiltration was found. The instructions do not attempt to bypass safety filters or override system constraints.
- [COMMAND_EXECUTION]: The Claude Code runtime configuration requests broad permissions, including
bash,webfetch, andwrite. These permissions are standard for the Claude Code environment to allow the agent to interact with the filesystem and the web to perform its tasks. No malicious use of these permissions is suggested in the skill's instructions. - [EXTERNAL_DOWNLOADS]: The installation instructions reference a vendor-specific command (
skills install peterfei/...). This is a legitimate installation pattern for the author's platform and does not involve untrusted third-party sources.
Audit Metadata