remote-run-curl
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to construct and execute
curlcommands that send shell instructions to a remote runner managed by BuildBuddy. Thestepsfield in the API request allows for arbitrary command execution on the remote infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill uses
persistent-fields.mdto store and retrieve configuration parameters that are automatically applied to future API requests. This creates a stateful injection surface where malicious instructions or flags could be persisted across sessions. - Ingestion points: The agent reads configuration from
persistent-fields.mdin theField persistencesection ofSKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious embedded content within the persisted fields.
- Capability inventory: The skill uses
curlto perform network operations and executes remote commands via the BuildBuddyRunAPI. - Sanitization: The instructions include a requirement for the agent to ask for user confirmation before writing to the persistence file, which serves as a manual checkpoint but does not programmatically sanitize the content.
Audit Metadata