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_navigation and lens_diagnostics ingest 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_navigation tool supports rename (file modification) and executeCommand (running server-side commands), while lens_diagnostics performs 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
Risk Level
SAFE
Analyzed
Sep 13, 2026, 06:03 AM
Security Audit — agent-trust-hub — pi-lens-lsp-navigation