seo

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.95). The skill’s runtime workflow for commands like /seo audit <url>//seo page <url> fetches outsider-authored free text from public web pages (via scripts/fetch_page.py downloading response.text, then scripts/parse_html.py extracting visible text/headings/meta) and feeds that extracted prose into the agent’s LLM context for analysis.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)