ln-210-epic-coordinator
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches missing configuration and reference files from the author's GitHub repository at 'levnikolaevich/claude-code-skills' using WebFetch when local 'shared' directories are absent.
- [COMMAND_EXECUTION]: Executes a local Node.js utility script 'shared/scripts/epic-planning-runtime/cli.mjs' during the finalization phase to record planning artifacts. It also interacts with system CLI tools like 'gh' (GitHub CLI) for issue management.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it extracts content from untrusted external sources (project requirements, architecture docs, and HTML files) to populate Epic descriptions and success criteria.
- Ingestion points: requirements.md, architecture.md, tech_stack.md, and project HTML files (scanned for functional domains).
- Boundary markers: None implemented; the skill directly interpolates extracted text into generated Epic documents.
- Capability inventory: The skill has permissions to create projects in Linear ('save_project'), create issues via GitHub CLI ('gh issue create'), and write to the local filesystem.
- Sanitization: No sanitization or validation of the ingested text is performed before it is used to generate instructions for the AI agent or task descriptions.
Audit Metadata