debugging-with-opensrc
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands, including
bun run opensrc:sync,bun run opensrc:use, andopencode run, primarily for environment synchronization and debugging tasks. - [EXTERNAL_DOWNLOADS]: The
opensrc:usecommand enables fetching external content from npm and GitHub. While the documentation highlights well-known libraries such as TanStack, TRPC, and Drizzle, this mechanism allows the introduction of external code into the local environment. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it directs the agent to analyze and act upon content from external source code repositories.
- Ingestion points: Files located within the
opensrc/repos/github.com/directory. - Boundary markers: The skill lacks explicit instructions or delimiters to ensure the agent ignores potential malicious directives embedded in the analyzed source code.
- Capability inventory: The agent utilizes file-reading tools (
mcp_read,mcp_grep) and command execution wrappers (bun,opencode). - Sanitization: No sanitization or validation of the external repository content is performed before analysis.
Audit Metadata