llm-wiki
Karpathy's LLM Wiki: build/query interlinked markdown KB.
45
50%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/research/llm-wiki/SKILL.mdSecurity
2 findings: 1 high severity, 1 medium severity. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill includes a concrete example that passes a plaintext password on the command line (`ob login --email <email> --password '<password>'`), which encourages embedding secrets verbatim in commands and could lead the LLM to ask for or output secret values directly.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill instructs creating and enabling a systemd service and explicitly calls "sudo loginctl enable-linger $USER" (and global npm install), which modifies system state and requires elevated privileges.
Low
Low-risk findings.
1 low severity finding. 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
This skill explicitly supports runtime ingestion of outsider-provided URLs/files/pasted text via `web_extract` / raw source capture, and that extracted readable content becomes part of the wiki and is then read/synthesized back into the agent’s LLM context during ingest/query.
- Repository
- NousResearch/hermes-agent
- Commit
d0d116b
- 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.