task-generation-mode

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell command substitution (!command) in the context section to execute git branch --show-current, git status --short, and cat AGENTS.md. These are standard non-privileged commands used to provide the agent with situational awareness of the repository state.\n- [PROMPT_INJECTION]: The skill is designed to ingest and analyze Product Requirements Documents (PRD), creating a surface for indirect prompt injection.\n
  • Ingestion points: Processes PRD files provided by the user or found in the workspace through functional requirement analysis.\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the PRD content.\n
  • Capability inventory: The skill can read repository files via cat, check git status, and generate new markdown files in the .planning/tasks/ directory.\n
  • Sanitization: No explicit sanitization or validation of the PRD content is mentioned in the instructions.\n- [EXTERNAL_DOWNLOADS]: The documentation includes an installation command using npx to fetch skills from a repository authored by 'ChristopherAlphonse'. This is a standard installation pattern for the platform and originates from the vendor's own namespace.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 03:33 AM