d2b-notice-search

Warn

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch instructions and updates from the @nomadamas/k-skill package from the npm registry.
  • [REMOTE_CODE_EXECUTION]: Running commands like npx -y @nomadamas/k-skill@0 instruct d2b-notice-search involves downloading and executing remote code from an unverifiable source. The skill also indicates a dependency on a local module d2b-notice-search via require().
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from the external D2B procurement website (www.d2b.go.kr). This represents a potential surface for instructions hidden in procurement notices to influence agent behavior.
  • Ingestion points: Browser-based extraction of bid notice titles, numbers, and categories from www.d2b.go.kr (instruction.md).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' warnings for the extracted content.
  • Capability inventory: The skill utilizes browser automation (Aside Browser) and CDP session management to interact with web pages.
  • Sanitization: There is no mention of sanitizing or escaping the data scraped from the procurement portal before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 1, 2026, 02:41 PM