skills/ruvnet/ruflo/agentdb-learning/Gen Agent Trust Hub

agentdb-learning

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructs the agent to use npx agentdb@latest, which downloads and executes the AgentDB CLI tool from the npm registry at runtime. These are vendor-provided resources from the author, ruvnet.
  • [COMMAND_EXECUTION]: The skill provides several shell commands using the npx utility for creating plugins, listing templates, and managing learning agents. These commands involve local file operations such as writing to the ./plugins directory and managing a local database at .agentdb/learning.db.
  • [DYNAMIC_EXECUTION]: The skill utilizes WebAssembly (WASM) for high-performance neural inference during the training of models. This involves executing binary code to accelerate machine learning tasks at runtime.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by ingesting external data into the agent's reinforcement learning loop.
  • Ingestion points: Untrusted experience data (state, action, reward) is ingested via the adapter.insertPattern method described in SKILL.md.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded content within the experience data are present in the provided examples.
  • Capability inventory: The skill possesses capabilities including command execution via npx agentdb and training/retrieval operations that influence the agent's future decision-making process.
  • Sanitization: There is no evidence of sanitization or filtering for the pattern_data ingested from external environment interactions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 06:40 PM