The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied MariaDB DDL scripts which could contain malicious instructions embedded in SQL comments. The skill lacks instructions for the agent to use boundary markers or to disregard instructions found within the processed data.\n
Ingestion points: The 'supplied DDL' or 'migration script' mentioned in SKILL.md and references/examples.md.\n
Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are defined in SKILL.md for handling external SQL content.\n
Capability inventory: All scripts in this skill are markdown or documentation based with no direct subprocess or network calls in SKILL.md or references/methods.md, but the skill is designed to guide an agent with such capabilities.\n
Sanitization: No sanitization, escaping, or filtering of external SQL content is described in SKILL.md or references/methods.md.\n- [METADATA_POISONING]: The SKILL.md frontmatter identifies the author as OpenAEC-Foundation, which differs from the provided vendor context impertio-studio. This discrepancy could mislead users regarding the skill's origin and reliability.

mariadb-agents-schema-reviewer