learn-reverse-engineering
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads lesson manifests, documentation, and lab materials from the author's GitHub repository (rohitg00/ai-engineering-from-scratch).\n- [REMOTE_CODE_EXECUTION]: The skill facilitates interactive labs by downloading and running code fixtures and scripts directly from the vendor's repository.\n- [COMMAND_EXECUTION]: The skill executes local shell commands for environmental checks, Python script execution, and utilizes system tools like clang and llvm-objdump.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, creating a potential attack surface for indirect prompt injection.\n
- Ingestion points: Fetches lesson documentation (docs/en.md) and quiz data from a remote repository.\n
- Boundary markers: The instructions lack specific delimiters to isolate ingested lesson content from the agent's core instructions.\n
- Capability inventory: The skill can execute shell commands and write progress tracking files to the local system.\n
- Sanitization: There are no documented routines for validating or sanitizing the content retrieved from the remote repository.
Audit Metadata