lsp-extract-function
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface through the processing of external source code.
- Ingestion points: Source code is read into the context via the mcp__lsp__open_document tool as described in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or ignore-instructions to isolate the ingested code content.
- Capability inventory: The skill utilizes mcp__lsp__apply_edit for file modifications and mcp__lsp__execute_command for server-side operations across all steps in SKILL.md.
- Sanitization: No explicit sanitization or filtering of the ingested code is documented.
- [EXTERNAL_DOWNLOADS]: The skill documentation (SKILL.md) references the agent-lsp MCP server located at github.com/blackwell-systems/agent-lsp as a requirement for functionality.
Audit Metadata