link-building

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The companion-check section instructs the agent to run shell commands that enumerate local skill directories and suggest installing missing skills via npx — a system-level probe and potential install flow unrelated to link-building and therefore a hidden/out-of-scope instruction.

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflows (e.g., "Execute broken link building" in SKILL.md and the manual inspection steps in references/link-audit.md) instruct the agent to fetch and inspect public third‑party webpages and backlink data from tools like Ahrefs/BuzzSumo/Connectively and then act on that content (qualify links, decide outreach or disavow actions), which clearly ingests untrusted public content that can influence subsequent tool use and decisions.