Is chipagosfinest/language-learning safe?
https://github.com/openclaw/skills/tree/main/skills/chipagosfinest/language-learning
This is a benign language education skill consisting entirely of conversational teaching instructions in markdown. It contains no executable code, no file system operations, no network requests, and no prompt injection patterns. All monitoring signals (filesystem, network, process execution, canary files) are clean with no anomalies attributable to the skill.
Category Scores
Findings (3)
INFO Standard persona instruction -5 ▶
The skill instructs the agent to adopt a 'polyglot language tutor' persona. This is standard practice for education skills and does not override system-level instructions or user preferences. The persona is narrowly scoped to language teaching.
INFO Large prompt surface area -5 ▶
The SKILL.md is extensive (~400 lines) covering 7 teaching modes, session structures, and adaptive teaching guidelines. While this is thorough for an education skill, the large surface area marginally increases the chance of unintended interactions with other skills in a multi-skill environment. No actual risk was identified.
INFO Lock file references external skill 0 ▶
The .clawhub/lock.json file references 'academic-research-hub' as an installed skill. This is metadata only and does not cause any code execution or dependency loading. It may indicate the author has other skills installed in their environment.