ai-marketing-claude-suite
Fail
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The installation instructions prompt the user to execute a shell script directly from a remote URL (https://raw.githubusercontent.com/zubair-trabzada/ai-marketing-claude/main/install.sh | bash). This allows arbitrary code execution on the local system from an unverified source.\n- [EXTERNAL_DOWNLOADS]: The skill relies on downloading and cloning code from an external GitHub repository (https://github.com/zubair-trabzada/ai-marketing-claude.git) that is not part of the verified or trusted vendor ecosystem.\n- [INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves fetching and analyzing content from arbitrary URLs using Python scripts (scripts/analyze_page.py). This creates an attack surface where a malicious website could host instructions designed to manipulate the AI agent's behavior during the audit process.\n
- Ingestion points: Untrusted data enters the agent context through
scripts/analyze_page.pywhich usesrequests.get(url)to fetch webpage content.\n - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands in the processed HTML data.\n
- Capability inventory: The skill possesses capabilities for network access, file system writes (generating reports), and launching subagents.\n
- Sanitization: The skill does not appear to sanitize or filter the fetched HTML content before providing it to the model agents.
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