NYC

developer-growth-analysis

Fail

Audited by Snyk on Feb 15, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The skill reads users' local chat history including pastedContents and instructs including "specific evidence" from chats and sending the full report to Slack without any redaction rules, so it can require outputting verbatim secrets (API keys, tokens, passwords) if present.

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly searches and ingests public, user-generated HackerNews content via Rube MCP to curate learning resources, which the agent will read and interpret as part of its workflow, exposing it to untrusted third-party content.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 09:12 PM