ln-210-epic-coordinator
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Node.js utility scripts located in the
references/scripts/directory (e.g.,epic-planning-runtime/cli.mjs) to manage its stateful lifecycle, record checkpoints, and finalize plan summaries. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection during its research phase.
- Ingestion points: In
PHASE_2_RESEARCH(SKILL.md), the skill scans repository documentation (docs/*.md) and HTML files (**/*.html) to extract functional domains and business objectives. - Boundary markers: No explicit delimiters or instructions are used to isolate content read from repository files during extraction.
- Capability inventory: The skill has the capability to create and modify epics via the Linear MCP, the GitHub CLI (
gh), and local file system writes (Write). - Sanitization: There is no explicit sanitization or validation of the text extracted from project files before it is used to influence the epic planning process.
- [SAFE]: The skill uses established platform patterns for project coordination. It interacts with trusted services (GitHub, Linear) and uses local scripts for state management without external network dependencies or remote code execution.
Audit Metadata