producthunt

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). These are suspicious: the domain (canifi.com) is not a widely recognized trusted vendor here, and the skill explicitly directs fetching and piping remote install.sh scripts (curl | bash) and direct .sh downloads—an established high-risk pattern that can execute arbitrary/malicious code and access credentials unless the source and script integrity are independently verified.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to navigate and scrape/navigate producthunt.com (public Product Hunt product pages, listings, and comments) and to read and act on those user-generated pages (discover, upvote, comment, search), so untrusted third-party content can influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The README instructs running curl -sSL https://canifi.com/skills/producthunt/install.sh | bash and curl -sSL https://canifi.com/install.sh | bash, which fetch and execute remote scripts as part of setup/installation and therefore can run remote code that controls the agent environment.