skill
blip-2-vision-language Review findings
orchestra-researchorchestra-research/ai-research-skillsupdated
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
- Stars
- 14,234
- Version
- v1
- Copies
- 0
Overview
Waxell's checks found 8 findings to review, highest severity high.
- Highest severity
- high
- Findings
- 8
- What ran
- Static analysis
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked 2 days ago
Result
Review findings Waxell's checks found 8 findings to review, highest severity high.
Checked with static analysis: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. Nothing was run. How the checks work
Findings (8)
high · 7
- high
Tells Claude to install unpinned packages (transformers, accelerate, torch, Pillow)
SKILL.md:46 · skill_risk:S2
- high
Tells Claude to install unpinned packages (salesforce-lavis)
SKILL.md:49 · skill_risk:S2
- high
Tells Claude to install unpinned packages (accelerate)
references/troubleshooting.md:12 · skill_risk:S2
- high
Tells Claude to install unpinned packages (transformers, accelerate, torch, Pillow, scipy)
references/troubleshooting.md:15 · skill_risk:S2
- high
Tells Claude to install unpinned packages (omegaconf, iopath, timm, webdataset)
references/troubleshooting.md:36 · skill_risk:S2
- high
Tells Claude to install unpinned packages (salesforce-lavis)
references/troubleshooting.md:37 · skill_risk:S2
- high
Tells Claude to install unpinned packages (torch, torchvision)
references/troubleshooting.md:51 · skill_risk:S2
medium · 1
- medium
Tells Claude to install packages (salesforce-lavis==1.0.2)
references/troubleshooting.md:33 · skill_risk:S3
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
One version so far: v1 (1.0.0), seen 2026-11-03.
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More research skills and plugins
cliporchestra-researchOpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval.… Review findingsResearchAI & agents14k
fine-tuning-serving-openpiorchestra-researchFine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference… Review findingsResearchData & analytics14k
fine-tuning-openvla-oftorchestra-researchFine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation,… Review findingsResearchEngineering14k
segment-anything-modelorchestra-researchFoundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or… Review findingsResearchAI & agents14k