# NousResearch/hermes-agent · Prompt injection defense via untrusted tool names

## Open now

- 1 issue, 1 PR open on GitHub.
- #98587: _UNTRUSTED_TOOL_NAMES doesn't cover terminal/execute_code/skill_view — indirect prompt injection can land through these tools too
- PR #101597: fix(security): frame side-door external content — web-cache reads, fetching shell commands, network code

These items address gaps in prompt-injection defenses by expanding _UNTRUSTED_TOOL_NAMES to cover terminal, execute_code, and skill_view, and by restricting how external content reaches the agent through web-cache reads, shell commands, and network code.

## TL;DR

- 3 member(s): 1 open issue(s), 0 closed issue(s), 1 open PR(s), 0 merged PR(s), 1 PR(s) closed without merging.
- No fix has been merged to main; one or more PRs were attempted (see below).
- **Recommended:** review the prior/competing PR(s) below. A fix was attempted but not merged; your case may extend or revive that work.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
- Pairwise link density `0.67`: the share of member 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.

## Open related issues

- #98587: _UNTRUSTED_TOOL_NAMES doesn't cover terminal/execute_code/skill_view — indirect prompt injection can land through these tools too

## Prior & competing PRs

- **#98663: fix(security): add terminal/execute_code/skill_view to _UNTRUSTED_TOOL_NAMES for prompt-injection defense**. closed without merge
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `#98587`
- **#101597: fix(security): frame side-door external content — web-cache reads, fetching shell commands, network code**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `agent/tool_dispatch_helpers.py`, `agent/tool_executor.py`, `tests/agent/test_tool_dispatch_helpers.py`, `website/docs/developer-guide/untrusted-tool-results.md`, `website/sidebars.ts`

## Fix status

- No merged fix on record.
- Subsystem: `agent`