rfc-lookup

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches the @mjpitz/mcp-rfc package from the official npm registry at runtime using the npx command.
  • [COMMAND_EXECUTION]: Shell commands are executed via python3 $MCP_CALL to interact with the RFC lookup server and its tools.
  • [PROMPT_INJECTION]: The skill processes content from external RFC documents, which creates a surface for indirect prompt injection.
  • Ingestion points: RFC content is ingested into the agent's context through the get_rfc, search_rfcs, and get_rfc_section tools (SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions defined in the skill to warn the agent to ignore potentially malicious instructions embedded within the retrieved RFC text.
  • Capability inventory: The skill's environment allows for network access (for document retrieval) and command execution (for tool operation) (SKILL.md).
  • Sanitization: No evidence of sanitization, filtering, or validation of the retrieved RFC content is present in the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 04:21 PM
Security Audit — agent-trust-hub — rfc-lookup