lsp-manager
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- COMMAND_EXECUTION (SAFE): The
scripts/check_server.shscript executes a hardcoded list of common language server binaries (e.g., gopls, pyright-langserver) with the--versionflag. This is a standard diagnostic check to verify software installation and does not involve untrusted input. - DATA_EXFILTRATION (SAFE): The skill does not perform any network requests or access sensitive user files such as credentials, tokens, or SSH keys. Data processing is limited to counting file extensions in the current project directory.
- PROMPT_INJECTION (SAFE): The documentation and instructions in
SKILL.mdare focused on technical configuration tasks. There are no attempts to override agent safety guidelines, bypass instructions, or extract system prompts. - INDIRECT_PROMPT_INJECTION (SAFE): The
scripts/detect_language.pyscript crawls the project directory but only processes file extensions for statistical purposes. It does not read file content or integrate untrusted text into the agent's prompt context, minimizing the risk of instruction hijacking through project files.
Audit Metadata