honcho
Configure and troubleshoot Honcho memory for Hermes.
55
64%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./optional-skills/autonomous-ai-agents/honcho/SKILL.mdLow
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The 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.
Why it was flagged
Honcho’s required runtime workflow injects a first-party “memory-context” block (session summary, user representation, and AI peer card plus recent messages) into the system prompt before each turn in `hybrid`/`context` recall modes, and those contents are derived from observed messages supplied by the end user, creating an indirect prompt-injection exposure path via user-authored text.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill calls the Honcho cloud service (https://app.honcho.dev) at runtime to obtain session summaries, user representations, and AI peer cards which are injected into the model's system prompt, so remote content directly controls agent prompts.
- Repository
- NousResearch/hermes-agent
- Commit
6680afb
- Audited
- Security analysis
Is this your skill?
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.