opensrc
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external, third-party source code into the agent's context. While this is the intended purpose, it creates a surface where comments or documentation in the fetched dependencies could attempt to influence the agent's behavior.
- Ingestion points: Dependency source code fetched from arbitrary external repositories and package registries via the
opensrccommand (SKILL.md). - Boundary markers: Absent; the instructions do not specify any delimiters or safety warnings for the agent when parsing the fetched content.
- Capability inventory: The agent has access to Bash tools (
rg,cat,find) to process the downloaded files (SKILL.md). - Sanitization: Absent; the agent is expected to read raw source files to understand internal implementations.
- [COMMAND_EXECUTION]: The skill relies on a specific command-line utility
opensrcand standard Unix tools (rg,cat,find) to operate. It interacts with the local file system by caching data at~/.opensrc/and resolving paths for the agent to use in subshells.
Audit Metadata