skills/mayrsascha/shumi-cli/shumi/Gen Agent Trust Hub

shumi

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx shumi to execute its functionality, which triggers the download and execution of the 'shumi' package from the NPM registry if it is not already present locally.
  • [COMMAND_EXECUTION]: The skill requires broad permission to execute shell commands via Bash(shumi *) and Bash(npx shumi *) to interact with its analysis engine.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by ingesting untrusted external data.
  • Ingestion points: Data enters the agent's context through shumi search (web search results) and shumi tweets (social media content).
  • Boundary markers: The instructions lack explicit delimiters or safety guardrails to prevent the agent from following instructions embedded within the fetched tweets or search results.
  • Capability inventory: The agent possesses shell execution capabilities, which could be abused if malicious instructions are successfully injected via external data.
  • Sanitization: There is no documented process for sanitizing, filtering, or escaping the external content before it is processed by the AI agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 08:34 PM