r14-borghei-claude-skills-seo

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation provides instructions to install the toolkit by cloning a repository from GitHub (github.com/SheenEmpress/r14-borghei-claude-skills-seo.git). This involves fetching external code from a source that is not listed among the trusted organizations or vendors.
  • [COMMAND_EXECUTION]: The project includes several shell command examples and bash scripts (daily-seo-check.sh, monthly-seo-report.sh) designed for automation and setup. These scripts involve file system operations and command execution in the user's local environment.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it is designed to ingest and analyze data from external websites (e.g., via /content-audit or /technical-seo). Malicious instructions embedded in those websites could attempt to influence the agent's behavior during the analysis phase.
  • Ingestion points: External URLs provided for audits, competitor domain data, and SERP analysis results.
  • Boundary markers: None identified; the documentation does not specify any delimiters or instructions for the agent to ignore embedded commands within the analyzed content.
  • Capability inventory: File system access for reports, tool execution, and network operations for auditing site performance.
  • Sanitization: There is no evidence of content sanitization or validation routines for data fetched from external URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 07:31 PM
Security Audit — agent-trust-hub — r14-borghei-claude-skills-seo