The Agent Skills Directory

[No Code] (SAFE): The skill is composed strictly of documentation (SKILL.md) and YAML metadata. It does not include any Python scripts, Node.js packages, or binary executables.
[External Downloads] (SAFE): The skill references 'https://rube.app/mcp' and 'composio.dev'. These are standard endpoints and documentation links for the Rube/Composio integration. No unauthorized downloads or 'curl | bash' patterns were detected.
[Indirect Prompt Injection] (LOW): The skill enables the agent to read external data from Linear (issues, comments). This creates a surface for indirect prompt injection where malicious text in a Linear issue could attempt to influence agent behavior. This is a known risk for any tool interacting with external data.
Ingestion points: LINEAR_SEARCH_ISSUES, LINEAR_GET_LINEAR_ISSUE (SKILL.md)
Boundary markers: None specified in the instructions.
Capability inventory: Data modification via LINEAR_UPDATE_ISSUE and LINEAR_RUN_QUERY_OR_MUTATION.
Sanitization: Not mentioned in the skill; relies on the agent's internal safety filters.

linear-automation