The Agent Skills Directory

[SAFE]: The skill defines a professional methodology for design evaluation and derivation. All instructions are focused on cognitive psychology principles and design protocols.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided artifacts like URLs and HTML snippets for evaluation. While this presents a surface for indirect prompt injection if the external content contains malicious instructions, this is inherent to the skill's core function of auditing designs and does not represent a malicious intent by the author.
[COMMAND_EXECUTION]: The documentation mentions a local script scripts/gen-pfd-index.py for regenerating the learning index. This is described as a development/maintenance utility for the practitioner and is not invoked automatically by the agent in a way that would bypass security boundaries.

pfd