The Agent Skills Directory

[EXTERNAL_DOWNLOADS] (HIGH): The skill instructs the installation of the Linear CLI via an untrusted Homebrew tap: brew install schpet/tap/linear. This source is not verified or listed as a trusted organization/repository, posing a supply chain risk.
[PROMPT_INJECTION] (HIGH): Vulnerable to Indirect Prompt Injection (Category 8).
Ingestion points: Untrusted data enters the agent context through linear issue list and linear issue view (which fetch issue titles and descriptions from Linear).
Boundary markers: No delimiters or safety instructions are used to separate external content from agent instructions.
Capability inventory: The skill can execute commands with side effects, including linear issue start (branch creation) and linear issue pr (creating GitHub PRs via the gh CLI).
Sanitization: No evidence of sanitization or validation of the retrieved issue content before it is used to populate PR descriptions or branch names.
[CREDENTIALS_UNSAFE] (MEDIUM): The skill guides the user to store a sensitive LINEAR_API_KEY in plain text within configuration files (.linear.toml) or environment variables, which may lead to accidental exposure or credential theft if the environment is compromised.
[COMMAND_EXECUTION] (LOW): The skill relies on executing various shell commands. While this is the intended purpose of a CLI wrapper, it increases the attack surface for the aforementioned injection vulnerabilities.

linear-cli