execute-linear-epic
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, including Linear issue descriptions, acceptance criteria, and repository documentation (local instructions, contribution docs). This content is interpolated into self-contained prompts for subagents. While this creates a surface for indirect prompt injection, the skill is designed for developer-led workflows and includes human-in-the-loop checkpoints for merges.
- Ingestion points: Linear API/MCP (epic and issue details), repository filesystem (docs, instructions).
- Boundary markers: None explicitly defined in the instructions for isolating external content within subagent prompts.
- Capability inventory: Git operations (branching, worktrees, commits, pushes, merges), execution of repository scripts, and interaction with the Linear API.
- Sanitization: No explicit sanitization or filtering of external content is mentioned.
- [COMMAND_EXECUTION]: The skill identifies and executes 'package scripts' and 'relevant checks' found within the repository. Executing repository-defined code is a standard function for this skill's primary purpose of software development orchestration.
- [DATA_EXPOSURE]: The skill accesses project-specific data via the Linear MCP and the local repository. There are no patterns indicating exfiltration to unauthorized third-party services.
Audit Metadata