writing-plans

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill translates user specifications into actionable tasks, creating a pathway where untrusted input influences generated code and commands.
  • Ingestion points: Ingests specifications or requirements provided in the task context.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the input spec.
  • Capability inventory: Generates Python code snippets and shell commands (e.g., git, pytest) for execution by subsequent agents or tools.
  • Sanitization: No explicit sanitization or validation of the input specification is mentioned.
  • [DYNAMIC_EXECUTION]: The skill generates implementation code and shell commands dynamically based on templates.
  • Evidence: The skill instructions define task structures that include code blocks and specific bash commands for testing and committing code.
  • Context: This activity is the primary, documented purpose of the skill and is limited to standard software development workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 01:43 PM
Security Audit — agent-trust-hub — writing-plans