supabase-fullstack

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill contains multiple examples and commands that embed API keys, tokens, and passwords directly into code and CLI commands (e.g., curl headers, PGPASSWORD, --db-password, hardcoded keys), which would force an LLM to emit secret values verbatim if real credentials are substituted into those templates.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to fetch public web content at runtime (e.g., https://supabase.com/changelog.md and linked docs) and then scan/follow it, which is outsider-authored free text that can be ingested into the LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to fetch and scan https://supabase.com/changelog.md and follow linked pages, so remote content would directly control the agent's behavior.