detrack
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
membraneCLI to interact with the DeTrack API, performing actions like searching connections and running tasks. - [EXTERNAL_DOWNLOADS]: The instructions guide the user to install the
@membranehq/clipackage via NPM, which is an official tool provided by the vendor. - [PROMPT_INJECTION]: The skill represents an indirect prompt injection surface through data retrieved from the DeTrack API. 1. Ingestion points: External data enters the agent context via
membrane action runandmembrane requestoutputs. 2. Boundary markers: No delimiters or instructions to ignore embedded commands are specified. 3. Capability inventory: The agent can execute shell commands and network requests using themembranetool. 4. Sanitization: No explicit sanitization of API responses is documented.
Audit Metadata