marketing-plan

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

• Third-party content exposure detected (low risk: 0.10). The required INIT workflow has the agent search and fetch outsider-authored web content, such as competitor pages, G2/Capterra reviews, and press for market sizing, without the outsider being able to force delivery into the workflow.

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

• Potentially malicious external URL detected (medium risk: 0.30). The decisive boundary is the inbound instruction at SKILL.md line 10 to read linked skill files "from the linked source" when they are not installed, and those files govern behavior (for example, secure-coding and anti-slop-writing). The publisher is the Quegenx/agent-skills GitHub repository, whose ownership is not established as a recognized vendor or foundation, so the dependency is common/reputable unofficial and rates medium.