tech-earnings-deepdive

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly requires ingesting and citing public, user-generated and open web sources (see "一手证据搜集标准" / Module A which lists Glassdoor/Blind, G2/AppStore, GitHub, SEC filings and demands at least three primary sources and tracing to original links), so the agent is expected to fetch and read untrusted third‑party content that can materially influence analysis and actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The README instructs installing the skill at runtime via the raw GitHub URL (/install-skill https://github.com/Day1Global/Day1Global-Skills/raw/main/tech-earnings-deepdive.skill), which fetches a remote .skill file that would be loaded as agent instructions and therefore directly controls prompts—this is a runtime fetch of external content controlling the agent.