skills/diodeinc/pcb/registry-search/Gen Agent Trust Hub

registry-search

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, specifically registry search results and board source code, which creates a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent context via pcb search results, pcb doc output, and content from git clone operations (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or warning markers for the ingested content.
  • Capability inventory: The skill has access to shell commands (pcb, git, diode_list_boards) and can perform network operations (SKILL.md).
  • Sanitization: There is no mention of sanitizing or escaping the external content before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with external resources to fetch information and source code.
  • Registry access: Fetches documentation and package data from the vendor's registry at code.diode.computer using the pcb doc command.
  • Git cloning: Clones external repositories via HTTPS for board inspection, though it specifies doing so outside the current checkout for safety.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute several CLI tools to perform its primary functions.
  • Tool usage: Utilizes pcb search, pcb doc, git clone, and diode_list_boards to interact with the filesystem and network.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 09:26 PM
Security Audit — agent-trust-hub — registry-search