landing-page-intel

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The script scripts/scrape_landing_page.py uses the requests library to fetch content from arbitrary external URLs provided by the user or agent. This constitutes a network operation to non-whitelisted domains, which is inherent to the skill's purpose but remains a monitored behavior.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from external web pages and returns it to the agent's context.
  • Ingestion points: External HTML content is fetched via requests.get() in scripts/scrape_landing_page.py.
  • Boundary markers: Absent. The skill does not provide delimiters or warnings to the agent to treat the scraped content as untrusted data.
  • Capability inventory: The skill performs network GET requests in scripts/scrape_landing_page.py.
  • Sanitization: The script uses regular expressions to extract specific data, but it explicitly captures potentially malicious payloads in HTML comments and data attributes through the extract_hidden_elements function, increasing the risk of the agent obeying hidden instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 09:58 PM