Skills
Navigate
skills/open-gsd/gsd-core/gsd-config/Gen Agent Trust Hub

gsd-config

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill extracts a model profile name from user-provided arguments and passes it directly to a shell command, creating an injection surface.
  • Ingestion points: The $ARGUMENTS variable is parsed in SKILL.md to extract the profile name string.
  • Boundary markers: Absent. The instructions do not specify any validation or sanitization of the input before it is used in a command.
  • Capability inventory: The skill is configured with the Bash tool and performs shell operations.
  • Sanitization: Absent. The user-provided string is interpolated directly into a gsd_run command call.
  • [COMMAND_EXECUTION]: The skill performs shell command execution to configure model profiles and verify system paths.
  • Evidence: SKILL.md contains instructions to execute command -v gsd-tools and gsd_run query config-set-model-profile <profile-name> --raw using the Bash tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 07:49 PM