Cairn
NousResearch/hermes-agent

False positives blocking prompt injection defense descriptions

Cluster 92644 · 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.

These issues address a scanner that incorrectly flags legitimate content describing or documenting prompt injection defenses as if it were itself a prompt injection threat. The focus is on reducing false positives when context files contain descriptive or educational framing about injection attacks.

Open issues1

  • Issue#92644False positive: scanner blocks SOUL.md content describing prompt injection defenses

Open PRs1

  • PR#121713fix(threat-scanner): stop blocking injection-defense doctrine as prompt injection

1 PR closed without merging

From the close comments: other 1

  • #92654 fix(security): don't block descriptive framing of prompt injection in context files · other
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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.

cluster/92644.json
cluster/92644.md