writing-plans

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a workflow for generating implementation plans based on external specifications, which presents a surface for indirect prompt injection.
  • Ingestion points: User-provided software specifications and requirements are used to populate the Markdown plan templates.
  • Boundary markers: Absent; the skill does not employ delimiters or explicit instructions for the agent to disregard commands potentially embedded within the requirement data.
  • Capability inventory: The workflow involves writing files to the local docs/plans/ directory and generating shell commands for Git operations and test execution.
  • Sanitization: Absent; the skill does not specify any validation or sanitization of input strings before they are interpolated into the implementation plans.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 01:29 PM
Security Audit — agent-trust-hub — writing-plans