The Agent Skills Directory

[SAFE]: The skill provides simple bash commands to list and get roadmap details from Linear. These commands are benign and directly support the skill's purpose of viewing roadmap information.
[PROMPT_INJECTION]: The skill processes data from the Linear API, which serves as a potential surface for indirect prompt injection attacks. 1. Ingestion points: External roadmap titles, descriptions, and metadata returned by linear-cli (SKILL.md). 2. Boundary markers: The skill does not include specific delimiters or instructions to ignore embedded commands in the roadmap data. 3. Capability inventory: The skill has access to the Bash tool (SKILL.md), allowing it to execute CLI commands. 4. Sanitization: There is no explicit sanitization or filtering of the roadmap content before it is processed by the agent.

linear-roadmaps