Reduce plugin-guard false positives on prose text
Cluster 103364. Data as of
Nothing open on GitHub. Fix merged in #111274 on 14 Sep 2026. Check it covers your case.
The short answer
- Known?
- Yes. 3 related items grouped here, 1 issue already closed.
- Fix event
- A fix was merged to main in PR #111274. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #111274. That is separate from the fix event. - Still open
- Nothing open on GitHub.
These items address the plugin-guard scanner incorrectly flagging explanatory prose, comments, and bare references in CLAUDE.md files as policy violations. The work narrows the scanner's detection logic to avoid blocking plugins over non-functional descriptive text.
Open issues0
Open PRs0
Fixes on record
-
#111274 Plugin scanner no longer hard-blocks plugins over prose and comments mentioning attack shapes (#103364, #111193; salvage #103383, #111199, #111204)
files:
tests/tools/test_plugin_guard.py,tests/tools/test_skills_guard.py,tools/plugin_guard.py,tools/skills_guard.py
1 PR closed without merging
From the close comments: merged via another change 1
-
#103383 fix(plugins): plugin-guard should not flag explanatory prose (#103364) · merged via another change →
bb1d255,#111274
Closed issues · 1
- Closed#103364plugin-guard false positives: context isolation prose and bare CLAUDE.md references
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structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
- Merged PRs
- #111274
- Closed issues
- 1
- Attempts
- 1 PR closed without merging
- Fix link checked
- 14 Sep 2026