seo-domain-analyzer

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill handles the APIFY_API_TOKEN and transmits it to api.apify.com via query parameters in the run_apify_actor function within scripts/analyze_domain.py. This is a security concern as URL parameters are often logged by web servers and proxies.
  • [COMMAND_EXECUTION]: The analyze_domain.py script allows writing output to paths specified via the --output and --markdown arguments. Without path validation, this could potentially be used to overwrite sensitive files if the agent is directed to an unsafe location.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes external Apify actors to perform its primary scraping functions. While Apify is a well-known service, the skill's functionality depends on these third-party scripts.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted text (keywords, competitor names, and SEO metadata) from scraped web content. (1) Ingestion points: External data enters the system through Apify actor datasets in the fetch_semrush_data, fetch_ahrefs_data, and check_keyword_rankings functions. (2) Boundary markers: There are no delimiters or instructions used to separate the external data from the agent's internal logic. (3) Capability inventory: The skill can perform network requests and write to the filesystem. (4) Sanitization: The script does not sanitize or validate the content of the strings returned by the scrapers before including them in the output report.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:03 PM