The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing external data (such as issue titles and descriptions) via the WebFetch tool without defined sanitization or delimiters. -- Ingestion points: External data retrieved from Linear API endpoints. -- Boundary markers: No explicit markers or 'ignore' instructions are present to differentiate between data and instructions. -- Capability inventory: Access to Bash, WebFetch, and Read tools. -- Sanitization: The logic does not currently include filtering or escaping of retrieved content.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool for local command execution; while this supports the intended automation, it represents a capability that could be targeted via manipulation.
[EXTERNAL_DOWNLOADS]: The skill documentation references official domains for Linear services, which are established and trusted platforms.

linear-pm