Is amankr-novo/deep-thinking safe?

https://github.com/openclaw/skills/tree/main/skills/amankr-novo/deep-thinking

97
SAFE

This skill is a benign reasoning framework that guides systematic thinking for complex tasks. It contains only markdown instructions with no executable code, no external URL references, no data exfiltration vectors, and no prompt injection patterns. All monitoring signals (filesystem, network, process execution, canary integrity) are clean.

Category Scores

Prompt Injection 95/100 · 30%
Data Exfiltration 100/100 · 25%
Code Execution 100/100 · 20%
Clone Behavior 100/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 95/100 · 5%

Findings (2)

INFO Broad behavioral activation scope -5 ▶

The skill defines very broad activation criteria covering 'multiple valid approaches', 'ambiguous requirements', 'architectural decisions', 'debugging', 'multiple systems or files', and 'high stakes'. This means it will influence agent reasoning on most non-trivial tasks. While this is the stated purpose of a thinking-framework skill and contains no malicious instructions, it represents a wide behavioral surface area.

INFO Dependency reference in lock.json -5 ▶

The .clawhub/lock.json file references 'academic-research-hub' version 0.1.0 as an installed skill dependency. This is metadata only and has no executable impact, but indicates the skill was developed in an environment with other skills installed.