agentkits-marketing-automation

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to install its components from the @aitytech/agentkits-marketing npm package and suggests cloning a repository from github.com/aitytech/agentkits-marketing.git.
  • [COMMAND_EXECUTION]: Manual installation steps involve copying files into platform-specific configuration directories (e.g., ~/.claude/agents/, ~/.claude/commands/), which affects the local environment of the AI assistant.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection attack surface.
  • Ingestion points: Commands such as /seo:audit, /competitor:deep, and /campaign:analyze in SKILL.md ingest untrusted data from external URLs and local files.
  • Boundary markers: There are no explicit boundary markers or warnings to disregard instructions embedded in the external content being processed.
  • Capability inventory: The skill has capabilities for network operations and file system access as detailed in the installation and integration sections of SKILL.md.
  • Sanitization: The documentation does not specify any sanitization, escaping, or validation of data retrieved from external sources before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 05:27 PM
Security Audit — agent-trust-hub — agentkits-marketing-automation