claude-code-marketing-skills

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

• Third-party content exposure detected (low risk: 0.10). The skills ingest external web pages and user-specified URLs via WebFetch/WebSearch and connected marketing/community platforms, falling under the low-risk category where the agent actively fetches specific URLs/sources.

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

• Potentially malicious external URL detected (high risk: 0.70). The installation instructions instruct the agent or user to execute a remote shell script from GitHub (https://raw.githubusercontent.com/cognyai/claude-code-marketing-skills/main/install.sh), which is an unofficial third-party repository providing executable setup content.