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
Bashtool to execute a localseoCLI utility andcurlfor API interactions with Bing and other search engines. - [PRIVILEGE_ESCALATION]: Instructions include creating a wrapper script at
~/.local/bin/seoand applyingchmod +xto 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.jsonand instructs the user to store Bing API keys in a localconfig.yamlfile. - [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 auditandseo agent-auditviaWebFetch. - 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), andWebFetch(network access). - Sanitization: Content is parsed for SEO scores and structured data without explicit sanitization or filtering of prompt-like text.
Audit Metadata