The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external CSV files, which is a common vector for indirect prompt injection attacks.
Ingestion points: External CSV data processed during analysis and transformation tasks described in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or instructions to treat data as untrusted.
Capability inventory: The skill utilizes Python and Pandas for data manipulation and analysis.
Sanitization: The guidelines include a recommendation to 'Always validate inputs before processing,' which serves as a defensive measure.
[METADATA_POISONING]: The author field in the skill's YAML frontmatter ('Claude Code') is inconsistent with the primary vendor context ('inbharatai') found in the documentation links.
[EXTERNAL_DOWNLOADS]: The skill includes a reference to a repository within the 'inbharatai' GitHub organization.
Evidence: Link to https://github.com/inbharatai/claude-skills found in the footer of SKILL.md.

csv-analyzer