The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content such as issue titles, descriptions, and comments retrieved from the Linear API, which constitutes untrusted external data.
Ingestion points: The agent retrieves external content using commands like linear issue view, linear issues list, linear search, and linear issue comment list as described in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or warnings for the agent to distinguish between its own instructions and the content retrieved from Linear.
Capability inventory: The skill utilizes Bash tools (linear, git, gh, curl, jq, grep, cat) with capabilities to read/write local files and perform network operations.
Sanitization: There are no explicit instructions for sanitizing or validating the data fetched from the API before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill documentation recommends the installation of an external Node.js package from a third-party repository.
Evidence: SKILL.md specifies the installation command npm install -g @0xbigboss/linear-cli in the setup section.
[COMMAND_EXECUTION]: The skill relies on executing the linear CLI and other shell utilities to perform management tasks.
Evidence: The allowed-tools section in SKILL.md permits various Bash commands, and the body of the skill provides numerous examples of shell-based interactions with the Linear platform, including git workflow integration and file system operations.

linear