pi-lens-lsp-navigation
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code files, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: The tools
lsp_navigationandlens_diagnosticsingest file paths and their contents from the workspace for analysis (SKILL.md). - Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat external code content as untrusted or to ignore embedded instructions within the analyzed code.
- Capability inventory: The
lsp_navigationtool supportsrename(file modification) andexecuteCommand(running server-side commands), whilelens_diagnosticsperforms active scans (SKILL.md). - Sanitization: The instructions do not define any sanitization, validation, or filtering for the data returned by the LSP or the code being analyzed.
Audit Metadata