aif-rules-check

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows least-privilege principles by using restricted shell commands (Bash(git *)) and performing only read-only operations on the filesystem.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data in the form of code diffs and project files to perform its compliance checks. This is the primary intended function of the skill.\n
  • Ingestion points: File content from the repository and git diff output (SKILL.md).\n
  • Boundary markers: Absent; the skill does not explicitly use delimiters to separate ingested code from its internal instructions.\n
  • Capability inventory: File reading (Read), pattern searching (Glob, Grep), version control (Bash(git *)), and user interaction (AskUserQuestion) (SKILL.md).\n
  • Sanitization: None; the skill processes file content as-is to verify compliance with the provided rules.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 06:55 AM