olares-market
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information such as application names, version numbers, and environment variables, which are used as arguments for olares-cli commands. This creates a potential surface for indirect prompt injection if the inputs are not properly sanitized.
- Ingestion points: User-defined parameters including application names, titles, and environment variables (e.g., GITEA_TOKEN) passed to market install, upgrade, and clone commands as seen in references/olares-market-lifecycle-add.md.
- Boundary markers: There are no explicit delimiters or instructions provided to separate user-provided data from the CLI command structure.
- Capability inventory: The skill enables the agent to execute lifecycle management operations (install, uninstall, upload, etc.) via the olares-cli tool, which interacts with the host system and platform services.
- Sanitization: The documentation does not describe any specific validation or sanitization routines for user input before it is used in command execution.
- [COMMAND_EXECUTION]: The skill's primary utility involves wrapping and executing system commands via olares-cli to manage applications. This is the intended behavior and is required for its functionality.
Audit Metadata