yistc-notion-issue
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill automates git operations, specifically the creation and management of worktrees within the
~/dev/worktrees/directory. - [COMMAND_EXECUTION]: Utilizes the GitHub CLI (
gh) to programmatically create commits, push branches, and open pull requests. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and act upon untrusted text from Notion issue titles, descriptions, and comments.
- Ingestion points: Reading Notion page properties and content in Step 1 (SKILL.md).
- Boundary markers: None present to distinguish instructions from Notion data.
- Capability inventory: Includes file system write access for code changes, shell command execution (git/gh), and Notion API write permissions.
- Sanitization: No explicit sanitization or validation of external Notion content is defined in the workflow.
Audit Metadata