composiohq-awesome-claude-skills-seo-content-marketing

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

• Third-party content exposure detected (low risk: 0.10). The workflow performs SEO content audits and analyses on websites and search results, which can ingest arbitrary web page content and search result text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs cloning and fetching from an arbitrary third-party repository (ColonyShopkeeper) during setup, establishing a weak and unverifiable operational dependency.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill includes a troubleshooting instruction to install system tools using sudo apt-get install curl jq, which prompts the agent to execute privileged commands.