better-planning-tasks
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads from user-controlled documentation files such as
<feature>-plan.mdandGLOSSARY.mdto generate task lists and GitHub issues. This ingestion of external data is a common pattern that introduces a surface for indirect prompt injection, where an attacker could embed instructions in the planning documents to influence the agent's behavior during task generation. - Ingestion points: Reads files from the
docs/better-planning/directory. - Boundary markers: The skill does not specify the use of delimiters or boundary markers when processing these documents.
- Capability inventory: The skill has the ability to write files to the local filesystem and execute GitHub CLI (
gh) commands to create issues and milestones. - Sanitization: There is no mention of sanitizing or validating the input text before it is used to generate tasks or transmitted to GitHub.
- [COMMAND_EXECUTION]: The skill provides instructions for using the
gh(GitHub CLI) tool to automate the creation of labels, milestones, and issues. These commands are scoped to the intended functionality of syncing plan milestones with a repository's issue tracker.
Audit Metadata