wos-parse-results

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill safely extracts bibliographic information using JSON parsing and DOM selectors. It does not perform network requests, file system access, or command execution.\n- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing external titles and abstracts.\n
  • Ingestion points: Extracts data from WoS API responses and DOM elements as described in SKILL.md.\n
  • Boundary markers: No protective delimiters are used for the extracted text fields.\n
  • Capability inventory: Data processing only; no access to high-risk system operations.\n
  • Sanitization: Includes a regex to strip HTML tags from abstracts, but lacks specific natural language sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 09:38 AM