tldr-overview

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a tldr CLI tool to perform static analysis (file tree, code structure, call graphs, and complexity) on the local project directory. These operations are aligned with the skill's functionality and do not perform unauthorized actions.
  • [SAFE]: The skill does not perform network requests, access sensitive system directories, or use obfuscated code. It operates exclusively on project source files to generate structural summaries.
  • [PROMPT_INJECTION]: The skill processes project source code as untrusted input. While this represents a surface for indirect prompt injection, it is an expected behavior for code analysis tools.
  • Ingestion points: Project source files (e.g., .py, .ts) processed via tldr subcommands in SKILL.md.
  • Boundary markers: None explicitly defined in the prompt instructions.
  • Capability inventory: Static analysis CLI commands including tree, structure, calls, and cfg.
  • Sanitization: No explicit sanitization of analysis output content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 10:17 PM
Security Audit — agent-trust-hub — tldr-overview