hermes-agent
Expert in building self-improving AI agents with tool use, multi-platform messaging, and a closed learning loop. Proficient in LLM orchestration, tool integration, session management, and agent autonomy.
42
42%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/hermes-agent/SKILL.mdSecurity
2 findings: 1 critical severity, 1 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
The list includes direct install scripts (astral.sh and raw.githubusercontent.com) that are piped to a shell in the provided instructions and a user-controlled MCP endpoint — direct remote scripts and personal endpoints are common vectors for malware and thus are high-risk.
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 document exposes multiple explicit bypasses and APIs that allow skipping dangerous-command approvals (e.g., /yolo toggle, --fuck-it-ship-it flag, terminal_tool.force) and describes patterns for privileged/system-targeting operations (systemctl, chown, /etc writes) while also providing an install-by-curl|bash entrypoint — together these enable an agent to modify system state or evade protections.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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.md contains two installation commands that fetch and execute remote shell scripts at runtime (curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash and curl -LsSf https://astral.sh/uv/install.sh | sh), which are runtime-executed external dependencies that run remote code.
- Repository
- fathah/hermes-desktop
- Commit
9bae718
- 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.