cs-create-tasks

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the codespring CLI to manage project data, including authenticating (codespring auth status), retrieving feature lists (codespring features), and reading detailed requirements (codespring prd <id>).\n- [EXTERNAL_DOWNLOADS]: The skill utilizes the @codespring-app/cli package via npx. This is an official vendor-distributed tool from the author 'CodeSpringApp' used for managing project tasks.\n- [PROMPT_INJECTION]: The skill processes feature notes and PRDs which are ingestion points for external data. This creates a surface for indirect prompt injection where embedded instructions could theoretically influence task generation.\n
  • Ingestion points: Feature notes and PRD content retrieved via codespring features and codespring prd <id> in SKILL.md.\n
  • Boundary markers: Not explicitly defined in the instructions.\n
  • Capability inventory: The skill can create new records in the project management system via codespring task create.\n
  • Sanitization: No specific sanitization logic is described for the content derived from notes and PRDs before it is used to generate task descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 09:20 AM
Security Audit — agent-trust-hub — cs-create-tasks