The Agent Skills Directory

[METADATA_POISONING]: There is a discrepancy between the verified skill author ('crazymsn') and the author identified in the skill metadata ('AHK Strategies'). This inconsistency in attribution can be misleading regarding the origin and maintenance of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted text from external sources to generate 'cognitive fingerprints', creating a potential surface for indirect prompt injection where malicious instructions hidden within the input text could attempt to subvert the agent's logic. Ingestion points: Processes user-provided text as described in the description and 'How to Profile' section of SKILL.md. Boundary markers: The instructions lack explicit requirements for using delimiters (e.g., XML tags or triple backticks) or 'ignore' instructions when processing the external content. Capability inventory: The skill utilizes 'Read' and 'Write' tools to perform its analysis and output results. Sanitization: No sanitization or filtering logic is specified for the input text before it is processed by the model.

dhdna-profiler