The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external text to extract "cognitive fingerprints" and "reasoning patterns."
Ingestion points: Processes any text provided by the user or from the conversation history for profiling purposes.
Boundary markers: The instructions lack explicit requirements for using delimiters or "ignore instructions" warnings when processing the input text.
Capability inventory: The skill is configured with Read and Write tool permissions, allowing it to access local files for analysis and save the generated profiles to the filesystem.
Sanitization: No specific sanitization or filtering of the source text is mentioned before it is processed by the agent's reasoning engine.

dhdna-profiler