context-search

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill implements a semantic code search feature using the vendor-specific tool jbcontext.
  • [COMMAND_EXECUTION]: The skill uses the jbcontext search command to explore the codebase. The execution pattern follows standard use cases for developer tooling provided by the author.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves code snippets from the local project, creating a theoretical surface for indirect prompt injection if the project code contains malicious instructions.
  • Ingestion points: Query inputs and retrieved codebase snippets (SKILL.md).
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: Execution of jbcontext CLI tool.
  • Sanitization: Not specified in the markdown body.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:38 AM
Security Audit — agent-trust-hub — context-search