supabase-policy-guardrails

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool with npx to run the ESLint utility as shown in the examples (references/examples.md). This is an expected behavior for code quality and security tools.
  • [PROMPT_INJECTION]: The skill is designed to analyze external source code, which creates a surface for indirect prompt injection attacks.
  • Ingestion points: Source code files read by the ESLint plugin defined in references/eslint-rules.md.
  • Boundary markers: The skill does not implement specific delimiters or instructions to ignore embedded commands in the files it processes.
  • Capability inventory: The skill is granted Read, Write, Edit, and Bash permissions in SKILL.md.
  • Sanitization: No explicit sanitization or filtering of external code content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 12:26 AM