nfse-integration

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the @bullcode/fiscal package directly from the author's GitHub repository (github:bullcodeapps/fiscal).
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and follow instructions from multiple external markdown documentation files located within the installed package directory. This creates a surface where the agent's behavior could be influenced by instructions hidden in those files.
  • Ingestion points: The agent is directed to read integration.md, dps-input.md, codes.md, and errors.md within the node_modules/@bullcode/fiscal/docs/ directory.
  • Boundary markers: No protective delimiters or warnings are used to prevent the agent from obeying instructions embedded in the ingested documentation.
  • Capability inventory: The agent is empowered to write implementation code and adapt logic based on these external files.
  • Sanitization: There is no mechanism to sanitize or validate the content of the documentation before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 12:24 PM