roadmap-strategist
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external project data from
.pm/backlog/items.yamland.pm/config.yaml. This constitutes a surface for indirect prompt injection; however, the skill uses this data exclusively for keyword matching and progress calculations (arithmetic). It does not pass this data to executable shells, network tools, or sensitive APIs, resulting in a safe assessment. - [DATA_EXPOSURE]: The skill limits its file system access to the project's
.pm/directory to manage roadmaps and configuration. This is a standard and safe practice for maintaining project-specific metadata and does not involve accessing sensitive system files or credentials.
Audit Metadata