Index of every page on this site: llms.txt
All skills
openclaw avatar

/autoreview

@0a5ba4b
by openclawopenclaw/agent-skills1.1k stars
126
Run it yourself

Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.

Use this Skill: https://skilld.dev/gh/openclaw/agent-skills/autoreview

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesimages.md

≈370 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Image review

  • Codex branch mode: added, single-frame PNG, JPEG and WebP files supported.

  • Install Pillow in helper's Python environment (python -m pip install Pillow). Use vision-capable Codex model + CLI supporting codex exec --image.

  • No new bypass flag required. Full decoding rejects corrupt/animated files.

  • Images: ≤16,777,216 pixels; no dimension >16,384 pixels. Decoder bomb warnings fail closed before pixel loading.

  • Added image paths: encoded bytes ≤20 MiB each, ≤100 MiB total; check Git object sizes before capture. Exceeding any limit fails entire review.

  • Capture exact bytes from pinned HEAD; stage only those images in isolated workspace; attach through Codex native image input.

  • Every pass: path, media type, byte count, SHA-256 manifest + image attachments

    • text diff. Image findings: original path, line 1.
  • Text-only review: no Pillow required.

  • Binary deletions, including images: deletion metadata in every mode; no image attachments or Pillow.

  • Other binaries, modified images, local/commit image additions/modifications, image review with other engines: unsupported; fail closed.

  • Missing Pillow or provider image limits: fail review; never silently drop assets.

  • Sensitive-path, source-mutation, authentication, sandbox controls stay enabled.

  • Partial clones: materialize required Git objects before review.

  • Isolated Git reader intentionally disables lazy network fetching; never weaken boundary.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alerttoday3 checks · Risk SAFE
  • Gen Agent Trust Hubtoday

    The autoreview skill is a specialized tool for performing automated code reviews using AI engines. It includes extensive testing fixtures and documentation focused on security, specifically addressing process isolation, environment sanitization, and the detection of credentials and vulnerabilities in code. All potentially suspicious patterns, such as dynamic code execution and hardcoded fake secrets, are confined to the test suite and are used to validate the tool's robustness and security boundaries.

  • Socket3d

    1 alert: gptSecurity

  • Snyktoday

    Risk: CRITICAL · 3 issues

Signed by skilld at 0a5ba4b. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 weeks ago

README badge

README badge for openclaw/agent-skills/autoreview