solo-seo-cli

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local seo CLI utility and curl for API interactions with Bing and other search engines.
  • [PRIVILEGE_ESCALATION]: Instructions include creating a wrapper script at ~/.local/bin/seo and applying chmod +x to it, which grants executable permissions to a dynamically created file.
  • [CREDENTIALS_UNSAFE]: The skill references a sensitive Google service account file at ~/.config/seo-cli/service-account.json and instructs the user to store Bing API keys in a local config.yaml file.
  • [INDIRECT_PROMPT_INJECTION]: The skill audits external websites by fetching and parsing content (HTML, robots.txt, llms.txt), creating a surface for potential injection of malicious instructions from untrusted external sources.
  • Ingestion points: Fetches content from user-provided URLs using seo audit and seo agent-audit via WebFetch.
  • Boundary markers: No explicit delimiters or instructions are used to ignore embedded directives in the fetched content.
  • Capability inventory: Includes Bash (command execution), Write/Edit (file modification), and WebFetch (network access).
  • Sanitization: Content is parsed for SEO scores and structured data without explicit sanitization or filtering of prompt-like text.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 11:41 AM