The Agent Skills Directory

[NO_CODE]: The skill consists entirely of instructional text and markdown templates for the AI agent to follow. It does not contain any executable scripts, shell commands, or network operations.
[DATA_EXPOSURE]: The skill references local framework files (e.g., ../../shared/frameworks/owasp-top10-2021.md) to populate security mappings. These are standard documentation files and do not expose sensitive user data or credentials.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied security terms, it uses them strictly for lookup and comparison purposes within a structured template. There is no evidence of unsafe interpolation or high-privilege capabilities that could be exploited via malicious input.

glossary