searching-packages

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the vendor-provided robomotion CLI to execute search queries and retrieve resource information. These operations are intended for local development and automation orchestration.
  • [DATA_EXFILTRATION]: The skill includes commands to list platform resources such as vaults, vault-items, and robots. While these represent sensitive configuration data, the access is facilitated through official vendor tooling for discovery purposes and does not indicate unauthorized data transmission.
  • [PROMPT_INJECTION]: The skill processes external data from package documentation (llms.txt) via the robomotion docs command, which presents a surface for indirect prompt injection. Ingestion points: Documentation content and search metadata retrieved from external package sources via the CLI. Boundary markers: Absent. Capability inventory: Subprocess execution of the robomotion CLI. Sanitization: No sanitization or filtering of external documentation content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 01:27 PM