The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructions include a command to download and execute a shell script directly from a remote URL.
Evidence: curl -fsSL https://raw.githubusercontent.com/lwlee2608/linear-cli/main/install.sh | bash in SKILL.md.
Context: The script is hosted on the skill author's personal GitHub repository and is necessary for installing the CLI tool required by the skill.
[COMMAND_EXECUTION]: The primary functionality of the skill relies on executing the linear CLI tool via subprocess calls.
Evidence: The skill defines workflows using linear issue get, linear issue search, and linear issue comment commands.
[PROMPT_INJECTION]: The skill processes untrusted content from Linear.app, which introduces a risk of indirect prompt injection.
Ingestion points: Remote data from Linear is retrieved using linear issue get (descriptions/comments) and linear issue search (titles).
Boundary markers: Absent. There are no explicit delimiters or instructions provided to the agent to treat retrieved issue content as data rather than instructions.
Capability inventory: The agent can execute CLI commands and potentially perform further actions based on the content read from Linear.
Sanitization: No sanitization or validation of the retrieved text is mentioned.

linear