tdn-lookup

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves technical documentation from tdn.totvs.com. This is the official developer network for TOTVS and is considered a well-known service for technical information.\n- [PROMPT_INJECTION]: The skill ingests data from an external website, creating a surface for indirect prompt injection.\n
  • Ingestion points: Technical documentation and API responses from tdn.totvs.com.\n
  • Boundary markers: The skill does not define explicit delimiters to isolate external content from the agent's instructions.\n
  • Capability inventory: The agent uses WebFetch, WebSearch, and browser automation tools (Playwright) to gather data and reads from several local reference files.\n
  • Sanitization: Mitigation is present through specific instructions to parse retrieved HTML/JSON and extract only technical fields such as Syntax, Parameters, and Examples, limiting the exposure to unprocessed remote content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 09:29 PM
Security Audit — agent-trust-hub — tdn-lookup