html-pr-review

Fail

Audited by Snyk on May 10, 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 explicitly instructs the agent to fetch and render raw diff hunks (inline in the HTML) and include file contents and line-level code, so any secrets present in the repository diffs would be reproduced verbatim in the artifact, creating an exfiltration risk.

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

  • Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md workflow explicitly instructs the agent to fetch PR data (e.g., "get the actual hunks via git diff <base>..<head>, the GitHub URL via MCP" and "read the PR description") which requires ingesting user-generated, public GitHub/PR content that the agent will read and use to make review decisions, so untrusted third‑party content can influence subsequent actions.

Issues (2)

W007
HIGH

Insecure credential handling detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
HIGH
Analyzed
May 10, 2026, 01:28 PM
Issues
2