kf-g-command-do-manual-fix-to-skill

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted content from Git diffs, which creates an indirect prompt injection surface where malicious code comments could influence the generated skill logic.
  • Ingestion points: Output from git status and git diff commands in SKILL.md.
  • Boundary markers: No explicit delimiters used for diff content, though the prompt instructs the AI to maintain a specific role.
  • Capability inventory: Executes Git commands and writes Markdown files to the local file system.
  • Sanitization: No automated sanitization; the workflow relies on mandatory human confirmation before rules are committed.
  • [COMMAND_EXECUTION]: The skill utilizes read-only Git subcommands (diff, status) to gather context about the codebase. These are used strictly for local analysis and do not include high-risk shell features or remote execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 06:01 AM
Security Audit — agent-trust-hub — kf-g-command-do-manual-fix-to-skill