skills-index-snippets
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill includes behavioral guidance using 'IMPORTANT' markers, such as 'Prefer retrieval-led reasoning'. These are categorized as natural instructional language relevant to the skill's functionality and do not attempt to bypass safety filters or override system instructions.
- [COMMAND_EXECUTION]: The documentation references local shell scripts for administrative tasks, such as './scripts/generate-skill-index-snippets.sh' and './scripts/validate-marketplace.sh'. These references describe legitimate maintenance workflows and do not involve unauthorized command execution or remote script downloads.
Audit Metadata