Indexing

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses curl -s https://ethskills.com/indexing/SKILL.md to fetch readable text from a public web page at runtime, which is outsider-authored free text that the agent ingests into its LLM context.

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

• Potentially malicious external URL detected (high risk: 1.00). The catalog explicitly directs runtime fetching and reading of https://ethskills.com/indexing/SKILL.md (via "curl -s https://ethskills.com/indexing/SKILL.md" and "Read https://ethskills.com/indexing/SKILL.md before querying chain data"), so external content would directly control agent prompts/instructions.