skills/kensaurus/skills/mushi-health/Gen Agent Trust Hub

mushi-health

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute various diagnostic commands using the vendor's mushi CLI and the supabase CLI. These commands probe component health, list API keys, and retrieve service status.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data by querying database tables and fetching edge function logs via the Supabase MCP. This creates an attack surface where external content could theoretically influence the agent.
  • Ingestion points: Supabase query_logs tool and SQL queries targeting the qa_story_runs table in SKILL.md.
  • Boundary markers: Absent; the skill does not define specific delimiters to isolate log content from instructions.
  • Capability inventory: Local command execution using mushi and supabase CLIs, and database interaction via MCP tools.
  • Sanitization: Not specified; the skill interprets raw log and database output for diagnostic purposes.
  • [DATA_EXPOSURE]: The diagnostic process involves verifying the reachability of the MUSHI_API_ENDPOINT and the validity of the MUSHI_API_KEY stored in ~/.mushirc. It also references the use of a SUPABASE_ACCESS_TOKEN for log retrieval, which is standard for development environment health checks.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 11:27 PM