llm-wiki-choose
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of Markdown instructions and metadata. It does not include any scripts, binaries, or command-line executions.
- [PROMPT_INJECTION]: The instructions do not contain patterns intended to bypass safety filters, override system prompts, or induce restricted behavior.
- [DATA_EXFILTRATION]: There are no commands that access sensitive files (such as credentials or SSH keys) or transmit data to external servers. The skill explicitly includes a safety gate to 'Stop before suggesting cloud ingestion for sensitive material'.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to browse and cite external sources like repository READMEs and official documentation. While this creates a surface for indirect prompt injection from third-party content, the skill includes mitigation instructions to mark uncertain tool claims as 'verify-before-use'.
- [EXTERNAL_DOWNLOADS]: No automated downloads or package installations are defined in the skill.
Audit Metadata