pm-humanprd
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is text transformation of local project documentation. It reads from
docs/pm-context/pm-context.mdand writes to defined subdirectories. These operations are restricted to the local workspace and do not involve sensitive system files or network access. - [SAFE]: No evidence of prompt injection or attempts to bypass AI safety constraints. The instructions are focused on formatting, narrative style, and decision tracking.
- [SAFE]: No obfuscation techniques, hidden commands, or external script downloads were detected. Includes references to documentation from Product Compass, an established product management resource site.
- [SAFE]: The skill does not use any dangerous shell commands, privilege escalation, or persistence mechanisms.
Audit Metadata