debugging-with-opensrc
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the retrieval of source code from trusted platforms, including GitHub and the NPM registry, using the
bun run opensrc:usecommand.- [COMMAND_EXECUTION]: Provides instructions for executing local development tools such asbunandopencode. It also includes aperlwrapper designed to implement execution timeouts during non-interactive testing sessions.- [PROMPT_INJECTION]: By instructing the agent to read and analyze content from external repositories viamcp_readandmcp_grep, the skill establishes a surface for indirect prompt injection. This is a characteristic of tools that process external data, where malicious instructions could theoretically be embedded in the source code being analyzed.
Audit Metadata