claude-rules

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill is composed entirely of markdown instructions and documentation. It does not contain any executable scripts, binaries, or automated code triggers.\n- [COMMAND_EXECUTION] (SAFE): The skill is authorized to use basic file management tools (Read, Write, Edit, Grep, Glob) for its intended purpose of managing documentation. No high-risk command execution or shell access is requested.\n- [DATA_EXPOSURE] (SAFE): No hardcoded credentials, API keys, or access to sensitive system directories (e.g., SSH keys, environment files) were identified.\n- [INDIRECT_PROMPT_INJECTION] (SAFE): The skill facilitates a workflow where the agent reads and follows rules from external files within the repository. While this creates a potential surface for indirect prompt injection if those files are maliciously modified, the skill itself provides legitimate documentation patterns.\n
  • Ingestion points: Project files located in .claude/rules/ and CLAUDE.md.\n
  • Boundary markers: The skill does not explicitly define delimiters for external content.\n
  • Capability inventory: File system access via Read, Write, Edit, Grep, and Glob tools.\n
  • Sanitization: No content sanitization or validation logic is defined for the rules the agent reads or writes.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:18 PM