research-codebase
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes local project validation and session management scripts located in
${CLAUDE_PLUGIN_ROOT}/scripts/for initialization and tracking. - [COMMAND_EXECUTION]: Interacts with project management and version control systems using the GitHub CLI (
gh) and thelinearisintegration tool. - [DATA_EXFILTRATION]: Performs automated synchronization of generated research documents to a remote service using the
humanlayer thoughts synccommand as a primary workflow step. - [EXTERNAL_DOWNLOADS]: Retrieves codebase context and architectural information from an external MCP service using the
mcp__deepwiki__ask_questiontool. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and summarizes untrusted codebase content.
- Ingestion points: Reads files and documentation via the
Readtool. - Boundary markers: None explicitly defined for isolating ingested code content.
- Capability inventory: File system access, shell command execution, and network-based data synchronization.
- Sanitization: No content sanitization is applied before the agent processes or summarizes the codebase data.
Audit Metadata