press-release-writing

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md Quick Start and Research & Fact-Checking sections explicitly instruct using the inference.sh CLI (e.g., infsh app run tavily/search-assistant, exa/search, exa/answer) to query and ingest public web/search results for research and fact-checking, meaning the agent will read and act on untrusted third-party content.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires and uses the inference.sh CLI (https://inference.sh) at runtime (e.g., "infsh app run ..."), which runs external apps (remote code) that the skill depends on to provide research/fact-checking, so this is a runtime external dependency that executes remote code.