local-seo-audit

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script 'scripts/local-seo-checker.py' to evaluate business data. It passes user-provided Name, Address, and Phone (NAP) information as command-line arguments.
  • [COMMAND_EXECUTION]: It reads configuration files and brand profiles from the user's home directory at '~/.claude-marketing/', which is used to manage marketing context and compliance rules.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its processing of external, untrusted data.
  • Ingestion points: Reads data from Google Business Profiles, external website URLs, and third-party review platforms.
  • Boundary markers: The process description does not include delimiters or instructions to ignore instructions embedded within the retrieved SEO data.
  • Capability inventory: The skill can execute local shell commands and read from the file system.
  • Sanitization: There is no specified mechanism for sanitizing or validating data fetched from external URLs before it is processed by the specialist agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 01:02 PM