mushi-health

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the mushi and supabase CLI tools to perform various system checks, including credential validation (mushi doctor), function status (mushi deploy check), and log retrieval (supabase functions logs).
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) as it processes data from untrusted external sources.
  • Ingestion points: External data enters the agent context via the output of get_logs and the results of SQL queries on the qa_story_runs table in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the ingested data.
  • Capability inventory: The skill has the ability to execute shell commands via the mushi and supabase CLIs and manage BYOK keys via the mushi keys commands.
  • Sanitization: No evidence of sanitization or validation of the log content or database records before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 11:19 AM
Security Audit — agent-trust-hub — mushi-health