Configure and troubleshoot Honcho memory for Hermes.
72%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./optional-skills/autonomous-ai-agents/honcho/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The skill configures Honcho memory, which ingests user conversations and messages to build user models injected into agent prompts, creating an indirect prompt injection risk via user-supplied chat input.
NousResearch/hermes-agent
e864515
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.