planning-contract

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation provides an installation command utilizing npx to fetch the legout/skills package from the author's repository.
  • [COMMAND_EXECUTION]: The skill documents a shell command (npx skills add) meant for users or automated installers to deploy the planning contract within an agent's environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for the agent to ingest and classify external documentation from project directories, which constitutes an indirect prompt injection vector.
  • Ingestion points: project/research/, project/adr/, project/specs/, project/plans/, and project/tickets/ directories.
  • Boundary markers: The contract enforces strict directory-based classification rules and requires explicit owner approval for document state changes.
  • Capability inventory: Not applicable; this skill file defines organizational rules and does not include executable scripts.
  • Sanitization: No explicit content sanitization or input filtering is mentioned for the processed artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 10:56 AM