multica-onboarding

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses vendor-specific tools via the Bash(multica *) capability to perform workspace operations, such as creating projects, generating issues, and adding autopilot triggers. This is consistent with the skill's stated purpose of workspace coordination.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface where data from an external kickoff profile is interpolated into a shell command. The Member IANA timezone is retrieved and passed directly to the multica autopilot trigger-add --timezone <IANA> command. * Ingestion points: The Member IANA timezone field within the kickoff profile block. * Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat this field as untrusted or to ignore embedded instructions. * Capability inventory: The skill has access to shell command execution via the Bash(multica *) tool. * Sanitization: The instructions do not specify any validation, filtering, or escaping for the timezone variable before it is interpolated into the shell command string.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 07:20 PM
Security Audit — agent-trust-hub — multica-onboarding