repo-research-analyst

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to perform systematic research on codebases, including mapping architecture, analyzing documentation, and identifying implementation patterns. No malicious behavior, data exfiltration, or unauthorized command execution was detected.
  • [PROMPT_INJECTION]: The skill processes untrusted data from repository files (such as README.md and CONTRIBUTING.md), which represents a surface for indirect prompt injection. However, this activity is inherent to its primary function as a research tool and no high-risk capabilities (like network exfiltration or system modification) are utilized in its instructions.
  • Ingestion points: Files are accessed through the Read tool, Grep tool, and Glob tool.
  • Boundary markers: None explicitly defined in the prompt instructions.
  • Capability inventory: Uses read-only search and file access tools (rg, ast-grep, glob).
  • Sanitization: No content sanitization is specified for the ingested file data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 01:21 AM