The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the agent to interact with the environment through the leanspec CLI. Key operations include capability discovery (leanspec capabilities), state visualization (leanspec board), and specification management (leanspec create, leanspec update, leanspec search, leanspec view). These commands allow the agent to read and modify the project's specification data and configuration.
[INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection due to its core functionality of reading and acting upon external specification data.
Ingestion points: Untrusted data enters the agent context through commands that read from the specification backend, such as leanspec board, search, and view (identified in SKILL.md and references/commands.md).
Boundary markers: There are no specific instructions for the agent to use boundary markers or delimiters to isolate data retrieved from external specifications from its primary instructions.
Capability inventory: The agent has the power to execute shell commands via the leanspec CLI and project-specific tools like pnpm for testing and linting (identified in references/workflow.md). It also possesses write capabilities to create or update items in the backend storage (local files or remote APIs).
Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the content retrieved from external sources before it is interpreted by the agent.

leanspec