cs-build-create-tasks

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the codespring CLI to interact with project features, notes, and tasks. These commands are necessary for the skill's primary function of build planning within the CodeSpring ecosystem.\n- [EXTERNAL_DOWNLOADS]: The skill executes the @codespring-app/cli package using npx. This is an official vendor resource provided to allow the agent to interface with the user's project data.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its ingestion of external documentation data.\n
  • Ingestion points: The skill reads feature descriptions, notes, and PRDs using codespring features and codespring prd <id> as defined in SKILL.md.\n
  • Boundary markers: No explicit boundary markers or "ignore instructions" warnings are used when interpolating this external content into the agent's context.\n
  • Capability inventory: The agent has write access to the user's Kanban board via the codespring task create command in SKILL.md.\n
  • Sanitization: There is no evidence of sanitization or strict schema enforcement for the documentation content before it is used to define task details.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 06:20 PM
Security Audit — agent-trust-hub — cs-build-create-tasks