Subagent auto-approve bypasses instruction-file protections
NousResearch/hermes-agent · cluster 120000 · agent
Data as of
3 open items. Fix attempted, not merged.
The short answer
1open issue
2open PRs
3items grouped
- Known?
- Yes. 3 related items grouped here, 0 issues already closed.
- Fix event
- No fix has been merged to main. see the attempts below.
- Tracker
- The maintainers' tracker marks this
unresolved. That is separate from the fix event. - Still open
- 1 issue and 2 PRs.
Next step: read the attempts below. Your case may extend or revive that work.
Pick up a Lab taskThese items concern a security gap where a delegated child agent's auto-approve callback can write to protected instruction files (AGENTS.md, SOUL.md, .cursorrules) without human approval. The group covers the bug report and related fix attempts targeting this gate.
Open issues1
- Issue#120000[Bug]: delegation.subagent_auto_approve lets a delegated child write AGENTS.md / SOUL.md / .cursorrules without any human approval
Open PRs2
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structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 0.36.1.00means 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 LabAt a glance
- Subsystem
- agent
- Closed issues
- 0
- Attempts
- 0 PRs closed without merging