analyze-and-convert
Analyze a HuggingFace model and attempt OpenVINO conversion — probe properties, run strategy matrix, classify failures, and produce a structured routing report.
57
66%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./.github/agents-prototype/skills/analyze-and-convert/SKILL.mdSecurity
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
The repository systematically enables execution of remote model/package code (trust_remote_code, pip-install git+ URLs, and adding --trust-remote-code to export) and posts gathered reports externally, creating a high-risk remote code execution / supply-chain / potential data-leak vector that could be abused as a backdoor.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
High: `probe-model` fetches HuggingFace model card/metadata JSON from `https://huggingface.co/api/models/...` and `try-conversion` runs `optimum-cli` exports on `MODEL_ID` (which pulls remote model/tokenizer/config), whose runtime error `stdout/stderr` and inferred text are then loaded by `classify-failure` (`all_errors` from `conversion_attempts.json`) and later included in `error_excerpts.json`/`conversion_report.md` that are used for downstream LLM context.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill installs git-backed packages at runtime (via pip) which fetch and execute remote code and are relied upon as strategy dependencies — e.g., git+https://github.com/huggingface/optimum-intel.git and git+https://github.com/huggingface/transformers.git.
- Repository
- openvinotoolkit/openvino
- Commit
4c20980
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.