The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to execute the @codespring-app/cli package from the NPM registry. This is an external dependency managed by the skill's author to provide core functionality.
[COMMAND_EXECUTION]: The skill executes multiple shell commands via the codespring CLI to manage project state, track tasks, and check authentication status. These are legitimate operations within the context of an orchestration skill.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests untrusted data from the CodeSpring platform to guide the agent's behavior.
Ingestion points: The skill reads PRDs and task lists using codespring prds and codespring tasks (SKILL.md, Steps 2 and 3).
Boundary markers: No explicit delimiters or instructions are provided to the agent to prevent it from following malicious commands that might be embedded in the project notes or PRD text.
Capability inventory: The skill can modify the local codebase, execute shell commands, and spawn up to five sub-agents with dynamic briefs.
Sanitization: There is no evidence of sanitization or validation of the externally sourced project data before it is interpolated into the agent's instructions.

cs-build-feature