skills/witooh/skills/state-db/Gen Agent Trust Hub

state-db

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it retrieves data from an external database for agent processing.
  • Ingestion points: Remote data is fetched from the Supabase REST API via SB_URL defined in SKILL.md.
  • Boundary markers: Absent; the skill does not specify the use of delimiters or 'ignore' instructions for retrieved content.
  • Capability inventory: The agent uses curl, jq, sed, and tail to execute operations.
  • Sanitization: Absent; no validation or escaping of the remote JSON payload is defined.
  • [COMMAND_EXECUTION]: Employs shell commands including curl for network requests and jq, sed, and tail for processing API responses.
  • [EXTERNAL_DOWNLOADS]: Communicates with external Supabase endpoints to fetch and update persistent state data.
  • [DATA_EXFILTRATION]: Transmits state information and session data to a remote database; the destination is managed via user-defined environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 04:10 AM