atxp

Fail

Audited by Snyk on Mar 4, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt explicitly tells the user/agent to run echo $ATXP_CONNECTION, which would print the secret value verbatim (exposing it in output) even though other usages rely on env vars, so it requires handling/outputting secrets directly.

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

  • Third-party content exposure detected (high risk: 0.90). This skill explicitly performs real-time web and X/Twitter searches (see SKILL.md Commands: npx atxp search <query> and npx atxp x <query>, plus the Usage and Programmatic Access sections) and instructs the agent to parse and present/summarize those results, meaning untrusted, user-generated third‑party content can influence subsequent actions.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 4, 2026, 05:48 AM