NousResearch/hermes-agent

Restricting agent model selection and config changes via allowlist

Cluster 128524 · agent. Data as of

2 open items. Fix attempted, not merged.

The short answer

1open issue
1open PR
3items grouped
Known?
Yes. 3 related items grouped here, 0 issues already closed.
Fix event
No fix has been merged to main. 1 PR closed without merging; see the attempts below.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
1 issue and 1 PR.

The members relate to an agent allegedly using cloud models outside a user's allowlist, a proposed hard security.model_allowlist setting to bound model choices, and a CLI change to refuse config writes launched from an agent session. They appear to be adjacent, with the bug report as the motivating concern and the others as possible safeguards, though the titles alone don't confirm that link.

Open issues1

  • Issue#128524[Bug]: Agent bypassed user's hard model allowlist, charged user's credit for unauthorized cloud models

Open PRs1

  • PR#136833fix(cli): refuse config writes launched from an agent session

1 PR closed without merging

From the close comments: closed without comment 1

  • #128665 feat(config): hard security.model_allowlist bounding every model Hermes picks for itself · closed without comment
How this cluster was grouped
  • Link evidence (structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
  • Pairwise link density 0.67: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. 1.00 means every pair is linked.

Pick up a Lab task

Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.

Open the Lab

At a glance

Subsystem
agent
Closed issues
0
Attempts
1 PR closed without merging

For your agent

The same facts, typed.