implementing

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands including git branch --show-current and project-specific verification tools such as make format or folder-specific Makefile targets. It also runs local Python scripts via hooks (plan_checkbox_reminder.py, plan_checkbox_stop.py) located in the vendor's plugin root directory.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it ingests and acts upon instructions from untrusted technical plans and source code.
  • Ingestion points: Technical plan files (Markdown/YAML) and codebase files read during the implementation process.
  • Boundary markers: Absent; the agent lacks explicit delimiters or instructions to disregard embedded commands within the processed data.
  • Capability inventory: The skill possesses the ability to write and edit files, perform git operations, and execute shell commands via build tools (make).
  • Sanitization: Absent; the skill does not implement validation or filtering for the content of the plans or files it processes before execution or interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 10:46 PM