The Agent Skills Directory

[Unverifiable Dependencies] (MEDIUM): The skill instructs the user to install the linearis package via bun add -g linearis. This package is not maintained by a source on the trusted organizations list, making it an unverifiable dependency with potential security implications if the package or its account is compromised.
[Indirect Prompt Injection] (LOW): The skill is vulnerable to indirect prompt injection as it processes data from Linear issues which can contain attacker-controlled content.
Ingestion points: Data is brought into the agent context via linearis issues read and linearis issues search (fetching issue titles, descriptions, and comments).
Boundary markers: There are no markers or specific instructions to the agent to ignore or isolate instructions found within the retrieved issue data.
Capability inventory: The skill has access to shell execution for linearis, git, and gh, and can modify external states (updating issues, creating branches, creating PRs).
Sanitization: There is no evidence of sanitization or validation of the data retrieved from the Linear API.
[Command Execution] (LOW): The skill relies on several command-line tools. While these are necessary for the skill's stated purpose, there is a minor risk of command injection if issue identifiers or other parameters provided by the agent are not strictly validated before being passed to the shell.

linear