The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and process data from external, potentially untrusted sources.
Ingestion points: The skill accepts inputs through the materialUrl, materialFile, and materialText fields as defined in references/form-schema.json, which can include content from arbitrary websites or documents.
Boundary markers: The instructions do not define clear delimiters or include specific guidance for the model to disregard instructions embedded within user-supplied materials.
Capability inventory: The execution logic in scripts/run.py has the capability to send this data to a remote API and return the resulting analysis to the user context.
Sanitization: There is no evidence of local sanitization or filtering of the input data before it is processed by the skill.
[EXTERNAL_DOWNLOADS]: The script scripts/run.py initiates network requests to the ai-skills.ai platform to perform its analysis and retrieve results.

ai-ab-testing