ai-marketing-claude-suite
Fail
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The primary installation method uses a 'curl | bash' pattern (
curl -fsSL https://raw.githubusercontent.com/zubair-trabzada/ai-marketing-claude/main/install.sh | bash). This executes unvetted code from an untrusted external repository with the permissions of the current user. - [EXTERNAL_DOWNLOADS]: The skill fetches resources from a third-party GitHub repository (
zubair-trabzada/ai-marketing-claude) that is not identified as a trusted vendor or official platform resource. - [COMMAND_EXECUTION]: The skill relies on local execution of shell scripts (
install.sh,uninstall.sh) and several Python scripts (e.g.,analyze_page.py,competitor_scanner.py) to perform its core functions. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via analyzed web content.
- Ingestion points: External URLs are fetched via
requestsand parsed withBeautifulSoupinscripts/analyze_page.py. - Boundary markers: None identified; untrusted web content is directly processed by subagents.
- Capability inventory: The skill has the ability to write files (
MARKETING-AUDIT.md,.pdfreports), execute local Python scripts, and utilize Claude Code shell tools. - Sanitization: There is no evidence of filtering or sanitizing HTML content to remove potential malicious instructions before it is presented to the LLM.
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/zubair-trabzada/ai-marketing-claude/main/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata