Who it is for
Use any model you want — Nous Portal, OpenRouter, OpenAI, your own endpoint, and many others. Switch with hermes model — no code changes, no lock-in.
README.md:21
PUBLIC REPORT · ADDED BY METAL MANTRA / AGENT SIGNAL v0.2
hermes-agent.
Scanned repository says: Use any model you want — Nous Portal, OpenRouter, OpenAI, your own endpoint, and many others. Switch with hermes model — no code changes, no lock-in.
nousresearch/hermes-agent scored 82/100 (BBB) on Metal Mantra's Agent Signal v0.2, from a static scan of 198 source files on Oct 12, 2026: 1 critical, 2 major and 2 minor findings; the most serious is "Dynamic code execution". An automated signal, not a security certification.
Metal Mantra scanned this public repository on its own initiative; the maintainer did not submit it. Maintainers: scan the repository yourself to take this report over, or contact us.
Inspect GitHub source0community interest
Votes show community interest, not safety. They never change this score.
82/100BBBNot security certification
Runtime safety, real-world agent capability, fitness for your use case or independent certification.
Scan scope198 / 5269Partial eligible-file selection · not the entire repository
Recorded findings5Heuristic matches requiring human review
SnapshotOct 12, 2026UTC · engine 0.5.1
DNS at scan timeUnverifiedDomain control is not security certification
What the source
actually tells us.
Structured, cited information from the scanned archive. Repository-authored claims are labeled and never treated as verified capabilities.
200 / 5269Partial selection
ReadRepository-authored information
2LICENSE, package.json
What it can do
No explicit capability or integration was extracted; that does not mean none exists.
What adoption takes
📖 Full documentation →
README.md:122Manifest declares Node.js ^22.22.0 || ^24.11.0 || >=26.0.0 as a requirement.
package.json:69Declares a dependency on js-yaml.
package.json:84Declares a dependency on semver.
package.json:85
Limits and terms
Manifest declares MIT as its license.
package.json:33
Observed technical context
TypeScript · 47 selected filesJavaScript · 2 selected filesPython · 142 selected filesModel API reference · static onlyTool-calling reference · static only
These are references in selected source files, not proof that a feature works at runtime.
Read from commit 2d9a76e at Oct 12, 2026, 10:42 AM UTC. Source links open that exact commit. Repository statements are unreviewed and do not affect the score.
02 / FINDINGS FIRSTWhat needs
What needs
a closer look.
Every finding is shown in full with the line it came from; secret values themselves are never printed. A matched pattern is a lead for investigation, not a confirmed vulnerability.
Dependencies: no lockfile or exact version pins at the repository root, so no advisory check was possible.
5 findings
CRITICALDynamic code execution
Dynamic code execution
The code runs text as code or as a shell command. If untrusted text such as model output or user input reaches it, an attacker can run their own commands.
Use an allow-listed dispatcher and argument-safe process calls.
MAJORModel call without fallback
Model call without fallback
A model call has no visible fallback. If the provider fails or is rate limited, the whole agent fails with it.
Configure a secondary model or explicit fallback path for provider failures.
MAJORDomain ownership not verified
Domain ownership not verified
Metal Mantra could not confirm that the owner controls the stated domain. The domain may belong to someone else.
Verify the domain using the Metal Mantra DNS TXT challenge.
MINORPrivacy Policy link not confirmed
Privacy Policy link not confirmed
No privacy policy link was found on the stated homepage. Buyers cannot see how the vendor handles their data.
Expose a clear Privacy Policy link on the official homepage.
MINORTerms link not confirmed
Terms link not confirmed
No terms link was found on the stated homepage. Buyers cannot see the conditions that apply to using the service.
Expose a clear Terms link on the official homepage.
The boundary
is part of the result.
- What was scanned
- 198 of 5269 eligible files · Partial selection.
Supported static source patterns and domain checks; no runtime execution. - What remains unknown
- Unscanned files, external dependencies, production configuration, actual agent behavior and evidence beyond the configured checks.
- Source location
- Links open the current repository HEAD. Source may have changed since this snapshot.
- Something looks wrong?
- Tell us if a finding, scope or claim on this report needs a correction. Report a problem with this report
- Entity trust · 15% of v0.2
- Includes DNS ownership, HTTPS and policy evidence. Verification is domain control, not a security certificate.DNS: unverifiedHTTPS: availablePrivacy: not confirmedTerms: not confirmed
Open the
calculation.
Each pillar starts at 100. Rule deductions reduce its score; weights determine the overall contribution.
Security & privacy
82/100
Guardrails & loop control
100/100
Schema & tooling
100/100
Token & cost efficiency
86/100
Entity trust
25/100
Did hermes-agent work for people?
No user reports yet.
Each report is one signed-in GitHub account saying what happened. We do not verify that the account ran the agent, and reports never change the automated score or grade. For a security problem, use the disclosure page instead of a public note.
SHARE THE EVIDENCEA signal.
A signal.
Not a seal.
Share the full report so its scope and limits travel with the score.
