seo-local

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines a verification process that involves running a local Node.js script via the Bash tool: node ${CLAUDE_SKILL_DIR}/../../scripts/validate-jsonld.mjs --url <u>. The use of the <u> placeholder in a shell command represents a potential command injection vector if the agent interpolates an unsanitized URL into the command string.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from external web pages via WebFetch.
  • Ingestion points: The skill fetches and analyzes the rendered_dom or raw_html of external websites.
  • Boundary markers: None; there are no instructions to wrap fetched content in delimiters or to disregard instructions found within the page content.
  • Capability inventory: The skill has access to the Bash (shell execution), WebFetch (outbound networking), and Read/Grep (file access) tools.
  • Sanitization: There is no mention of sanitizing or validating the content of the fetched web pages before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 08:09 PM
Security Audit — agent-trust-hub — seo-local