hermes-tweet

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and install the Hermes Tweet plugin from a GitHub repository (Xquik-dev/hermes-tweet) using the hermes CLI.
  • [COMMAND_EXECUTION]: The skill uses the hermes command-line utility to manage plugins (install, enable, list), representing routine administrative operations for the intended environment.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and process untrusted data from X/Twitter.
  • Ingestion points: Data enters the context through tweet_read workflows, including searches, tweet lookups, and account monitoring (SKILL.md).
  • Boundary markers: No explicit delimiter or "ignore instructions" warning is implemented for processed tweet content.
  • Capability inventory: The skill can perform authenticated actions like posting, direct messaging, and media changes when HERMES_TWEET_ENABLE_ACTIONS is set to true (SKILL.md).
  • Sanitization: There is no documented sanitization or filtering of the external social media content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 03:31 AM
Security Audit — agent-trust-hub — hermes-tweet