better-planning-sync

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests git diffs from the project build which represents an attack surface for indirect prompt injection.
  • Ingestion points: Git diff of the source code (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters to isolate diff content from the agent's internal reasoning.
  • Capability inventory: The agent can write to markdown and HTML files, and perform git commits (SKILL.md, references/doc-layout.md).
  • Sanitization: No specific sanitization or filtering of the diff content is mentioned.
  • [COMMAND_EXECUTION]: The skill performs shell command execution to manage the reconciliation workflow.
  • Evidence: Execution of git to retrieve changes and commit documentation updates.
  • Evidence: Use of xdg-open or open to prompt the human to view generated HTML artifacts (references/html-artifacts.md).
  • Evidence: Conditional execution of canvas/scripts/render_diagram.mjs to render diagrams if the canvas tool is available (references/html-artifacts.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 08:30 PM
Security Audit — agent-trust-hub — better-planning-sync