supabase-detect

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a surface for indirect prompt injection attacks.
  • Ingestion points: The skill fetches and analyzes HTML source code, JavaScript bundles, and network patterns from arbitrary target URLs provided by the user (SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potentially malicious instructions embedded within the fetched HTML or JavaScript content.
  • Capability inventory: The skill possesses extensive local file-writing capabilities, including the creation and modification of .sb-pentest-context.json, .sb-pentest-audit.log, .sb-pentest-evidence/ files, curl-commands.sh, and timeline.md (SKILL.md).
  • Sanitization: The instructions do not specify any sanitization, filtering, or validation of the external content before it is processed or used to generate file outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:43 PM
Security Audit — agent-trust-hub — supabase-detect