repowiki-generator

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts, scripts/analyze_project.py and scripts/generate_metadata.py, to automate project scanning and metadata generation. These scripts utilize only standard libraries and run locally.
  • [PROMPT_INJECTION]: The skill processes untrusted local source files to generate summaries, which creates an indirect prompt injection surface.
  • Ingestion points: Project source code files are read by the analysis script and the agent.
  • Boundary markers: No specific delimiters are implemented for source code ingestion.
  • Capability inventory: Local filesystem write access (to create the wiki/ directory) and command execution for local scripts.
  • Sanitization: Not explicitly mentioned for the ingested file contents.
  • [SAFE]: No malicious patterns, obfuscation, or data exfiltration were detected. The skill follows security best practices by explicitly excluding sensitive directories such as .git, .env, and node_modules from its scanning process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 01:36 AM