webflow-schema

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, which could lead to indirect prompt injection if the agent follows instructions hidden within the processed content.
  • Ingestion points: scripts/audit_jsonld.py fetches and parses HTML content from arbitrary URLs; scripts/check_bindable_text.py reads data from user-supplied CSV files.
  • Boundary markers: Absent. Data from external sources is printed to the console without delimiters or instructions to the agent to ignore embedded commands.
  • Capability inventory: scripts/audit_jsonld.py performs network requests; scripts/check_bindable_text.py and scripts/search_references.py perform file system reads.
  • Sanitization: While scripts/search_references.py includes a filter (_INJECTION_RE) for common injection patterns, the primary data processing scripts (audit_jsonld.py and check_bindable_text.py) do not sanitize content before outputting it to the agent's context.
  • [DATA_EXFILTRATION]: The script scripts/audit_jsonld.py uses the urllib.request.urlopen function to retrieve content from user-specified URLs. This performs network operations to non-whitelisted domains. While functional, it could also be misused to access internal resources or read local system files via the file:// protocol if the agent is directed to access local paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 10:18 PM