repo-to-skill

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses git clone to download content from external GitHub repositories specified by the user.
  • [COMMAND_EXECUTION]: Uses shell commands including git clone and cp to manage repository files and move documentation into the skill's reference directory.
  • [PROMPT_INJECTION]: Exhibits an indirect prompt injection surface (Category 8) by processing and extracting information from untrusted external codebases.
  • Ingestion points: Contents of source code, documentation, and metadata files from repositories cloned via GitHub or accessed through local paths.
  • Boundary markers: The workflow lacks specific delimiters or instructions to treat repository content as untrusted data separate from the agent's operational logic.
  • Capability inventory: The skill possesses the ability to read and write files, execute shell commands, and spawn subagents to process data.
  • Sanitization: No procedures are defined for sanitizing, escaping, or validating the content extracted from repositories before it is incorporated into the final skill files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 11:52 AM
Security Audit — agent-trust-hub — repo-to-skill