docs-draft-workflow-docs
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation guidelines and source code from official Elastic domains (elastic.co) and GitHub repositories (github.com/elastic). These are trusted vendor resources.
- [COMMAND_EXECUTION]: Employs the GitHub CLI (
gh issue view) to retrieve issue metadata, descriptions, and comments to inform the documentation drafting process. This is confined to specific repositories and necessary for the skill's functionality. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub issues and comments which are then used to generate documentation drafts.
- Ingestion points: GitHub issue body and comments are processed in
SKILL.md(Step 0). - Boundary markers: The instructions lack explicit delimiters to isolate untrusted content from the system prompt.
- Capability inventory: The skill has the ability to write files to the local workspace and execute GitHub CLI commands.
- Sanitization: No specific sanitization or filtering logic is defined for the input content.
Audit Metadata