skills/ming-kang/skills/archive/Gen Agent Trust Hub

archive

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git diff --stat <baseline>..HEAD to provide context for the summary. The baseline commit is retrieved from the project's local file frontmatter.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes data from local files (.biu/SPEC.md, .biu/tasks/*.md) to generate its summary. * Ingestion points: Local workspace files in the .biu/ directory. * Boundary markers: None identified in the prompt logic. * Capability inventory: Local file operations and git command execution. * Sanitization: The skill does not validate or sanitize file contents before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 05:29 AM