The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and displays issue titles, descriptions, and comments from the Linear API, which are external, potentially attacker-controlled sources.
Ingestion points: The scripts/linear.sh script fetches data via the issue, standup, and team commands, which the agent then processes to summarize status or display details.
Boundary markers: No specific delimiters or safety instructions are used when displaying issue content to the agent.
Capability inventory: The agent has capabilities to execute shell commands (via the provided script) and is instructed in SKILL.md to use developer tools like git and gh (GitHub CLI).
Sanitization: The skill does not sanitize or filter the content retrieved from Linear before presenting it to the agent.
[COMMAND_EXECUTION]: The skill documentation provides detailed instructions for the agent to perform complex Git operations, including git worktree and git push, as well as creating pull requests using the gh CLI tool.
[EXTERNAL_DOWNLOADS]: The skill communicates with api.linear.app, which is the official GraphQL endpoint for the Linear service. These network operations are necessary for the skill's primary purpose and target a well-known service domain.

linear