ml-model-extraction
Extract a functional clone of a black-box ML model via prediction API queries, and infer whether specific records were in the training set (membership inference).
74%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./packages/decepticon/decepticon/skills/standard/analyst/ml-model-extraction/SKILL.mdE006: 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
This document contains explicit, actionable instructions and code to perform unauthorized model extraction and membership inference (data/model theft) along with operational evasion techniques, indicating deliberate malicious intent.
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.md includes explicit runtime commands that clone and execute remote code from https://github.com/ftramer/Steal-ML (git clone ...; pip install ...; python steal.py), so the skill fetches and runs external code at runtime.
- 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.