Skip to content

fix: exclude binary and large files from LLM analysis#307

Open
Makia9879 wants to merge 1 commit into
NVIDIA:mainfrom
Makia9879:feat/filter-llm-input-files
Open

fix: exclude binary and large files from LLM analysis#307
Makia9879 wants to merge 1 commit into
NVIDIA:mainfrom
Makia9879:feat/filter-llm-input-files

Conversation

@Makia9879

@Makia9879 Makia9879 commented Jul 24, 2026

Copy link
Copy Markdown

Summary

Skip image, audio, and video files when creating LLM analysis batches.

Changes

  • Add a list of supported media file extensions.
  • Exclude matching media files from LLMAnalyzerBase.get_batches().
  • Add regression tests for media filtering.
  • Preserve existing behavior for source files and SVG content.

Verification

  • 1393 passed
  • 12 skipped
  • 6 xfailed
  • Ruff lint and formatting checks passed.

Signed-off-by: Makia98 <makia98@foxmail.com>
@Makia9879
Makia9879 force-pushed the feat/filter-llm-input-files branch from 93b68fe to 41b5110 Compare July 24, 2026 10:26
@Makia9879
Makia9879 marked this pull request as ready for review July 24, 2026 10:27

@rng1995 rng1995 left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[Automated SkillSpector Review]

Requesting changes because the filter uses attacker-controlled filename suffixes as a binary predicate and does not implement the PR title's large-file exclusion. A text payload named .png is removed from semantic analysis, while extensionless binaries and arbitrarily large text files are still batched. Please base skipping on inspected content or trusted metadata, define and test the size rule, and preserve scan-completeness accounting for skipped files.

Comment thread src/skillspector/llm_analyzer_base.py
@Makia9879
Makia9879 requested a review from rng1995 July 24, 2026 16:04
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants