The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface (Category 8) where malicious instructions in analyzed text could potentially influence agent behavior.
Ingestion points: The skill processes untrusted data provided by the user for profiling and accesses conversation history in 'Self-Profile Mode' as described in SKILL.md.
Boundary markers: The instructions lack explicit boundary markers or directions to ignore instructions embedded within the text being analyzed.
Capability inventory: The skill is configured with Read and Write tools, which are used to process input text and generate the cognitive profile output.
Sanitization: There is no evidence of input validation or sanitization mechanisms to filter or escape commands found in the input text.
[SAFE]: The skill references external research papers and project resources from legitimate sources, including Zenodo and official project domains.

dhdna-profiler