setup-system-thinking
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads and installs external agent skills using the
npx skills addcommand. - Sources include the vendor's own repository
JustYannicc/skillsand a known third-party repositorymattpocock/skills. - These downloads are the primary purpose of the skill and are performed through a standard package manager for the agent environment.
- [COMMAND_EXECUTION]: The skill executes shell commands to manage the lifecycle of other skills.
- It runs
npx skills add,npx skills remove, andnpx skills listto modify the agent's capabilities. - The instructions include explicit safeguards, requiring the agent to present plans to the user and receive confirmation before executing removal or installation commands.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests and modifies configuration files (
AGENTS.mdandCLAUDE.md). - Ingestion points: Reads existing agent configuration files and skill listing metadata.
- Boundary markers: Employs specific HTML-style comment tags (
<!-- systems-thinking-suite:begin -->) to delineate its managed content and prevent interference with other instructions. - Capability inventory: The agent can write to files and execute package management commands.
- Sanitization: The skill relies on structured markers and user review to ensure that only approved changes are applied to the configuration files.
Audit Metadata