dido-planning

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a purely procedural documentation and planning workflow. It instructs the agent to create and maintain Markdown files (e.g., PROJECT_CHARTER.md, ROADMAP.md, and plans) within a project's docs/ directory to manage state across sessions.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to treat external documentation (PROJECT_CHARTER.md) as the primary source of truth for product requirements. This introduces a surface for indirect prompt injection where instructions embedded in the charter or Figma briefs could influence the agent's behavior. However, this is a standard operational risk for planning skills, and the skill lacks sensitive capabilities (like network exfiltration or arbitrary command execution) that would facilitate an attack.
  • Ingestion points: docs/PROJECT_CHARTER.md, docs/ROADMAP.md, docs/plans/, and Figma briefs.
  • Boundary markers: Not explicitly defined in this skill; relies on the agent's internal interpretation of document structure.
  • Capability inventory: File system read/write for documentation purposes. No network or subprocess execution found in this skill.
  • Sanitization: None explicitly mentioned for processing the charter content.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 02:26 PM