llm-tldr
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- Command Execution (SAFE): The skill instructs the agent to perform standard environment setup (python3 -m venv) and install a local vendored tool (pip install -e tools/llm-tldr). These are expected behaviors for a CLI-based tool integration.
- Indirect Prompt Injection (LOW): The skill processes external repository data (symbols, structure, and text) to provide summaries. While this creates a surface for indirect prompt injection if the scanned files contain malicious instructions, this is an inherent risk of repository analysis tools and no specific exploits were found in the instructions.
- Data Exposure (SAFE): The tool manages local indexes and configuration in a hidden directory (.tldr/) within the project root. It reads repository content for context but does not demonstrate any patterns of external data exfiltration.
Audit Metadata