agentic-skills
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a procedural framework for software engineering (spec-writing, planning, TDD, and review). It does not contain executable code, malicious prompt injections, or unauthorized data access patterns.
- [EXTERNAL_DOWNLOADS]: The skill references an external GitHub repository (github.com/addyosmani/agent-skills) for installation instructions and project source. These are documented as standard plugin installation procedures for AI agents.
- [COMMAND_EXECUTION]: The skill contains example commands for plugin installation (e.g.,
/plugin marketplace add,gemini skills install) and git operations (git clone). These are illustrative and typical for developer tooling skills. - [PROMPT_INJECTION]: No malicious override or bypass instructions were detected. The skill uses 'IMPORTANT' and 'CRITICAL' internally within its documentation to emphasize engineering quality rather than to manipulate the underlying AI's safety protocols.
Audit Metadata