add-karpathy-llm-wiki
Warn
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various shell commands to create directories, modify project configuration files (using perl regex), and restart system services via
launchctl(macOS) andsystemctl(Linux). - [REMOTE_CODE_EXECUTION]: During setup, the skill runs local executable scripts including
setup/index.tsviapnpm exec tsxandsetup/lib/install-slug.shusingsource. This allows for the execution of code logic stored outside the skill's primary instruction files. - [EXTERNAL_DOWNLOADS]: The skill defines a pattern for fetching external documents using
curlto ensure full content ingestion for the wiki knowledge base. - [PROMPT_INJECTION]: The skill is designed to ingest and process arbitrary external data (URLs, PDFs, etc.) into a persistent wiki. It lacks clear sanitization or boundary markers to isolate source content from the agent's instructions, creating a surface for indirect prompt injection.
- Ingestion points:
sources/directory and external URLs. - Boundary markers: None present in the instructions to the agent for processing source files.
- Capability inventory: File system writes, shell command execution, service management, and dynamic skill generation.
- Sanitization: No sanitization or validation of content from external sources is specified.
Audit Metadata