The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external files (CSV, JSON), API endpoints, and databases, creating a surface where malicious instructions could be embedded in the data to influence agent behavior.
Ingestion points: SKILL.md defines CSV/JSON files, API endpoints, and Database queries as primary data sources for evaluation.
Boundary markers: The instructions do not include specific delimiters or 'ignore embedded instruction' warnings for the data being processed.
Capability inventory: The skill is primarily focused on generating analysis and scores; it does not request access to high-risk tools like shell execution or arbitrary network writing in its configuration.
Sanitization: The skill lacks specific instructions for sanitizing or filtering input data to remove potential prompt injections.

seo-programmatic