repo-skillopt

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard system commands including rg (ripgrep), grep, and git ls-files to efficiently search and map the repository structure.
  • [COMMAND_EXECUTION]: It incorporates a custom command-line interface, reposkillopt-engine, for performing deterministic code analysis, such as identifying refactoring opportunities and tracing workflows.
  • [PROMPT_INJECTION]: The skill operates by ingesting and analyzing untrusted data from legacy repositories (code, documentation, and configuration files), presenting a surface for indirect prompt injection.
  • Ingestion points: Repository source code, manifests, CI workflows, and documentation.
  • Boundary markers: None explicitly defined for input data; the output follows a structured labeling system.
  • Capability inventory: File system access, shell command execution, and custom analysis tool invocation.
  • Sanitization: The instructions do not specify sanitization or validation of the ingested repository content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 09:26 PM
Security Audit — agent-trust-hub — repo-skillopt