The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review external JavaScript source code and browser execution paths. This creates a theoretical surface for indirect prompt injection where malicious instructions could be embedded in the code being analyzed. However, the skill provides only review logic and lacks any dangerous capabilities (such as network access or file writing) that could be exploited by such an injection.
[DATA_EXPOSURE]: The documentation in references/rule.md contains a local absolute file path (/Users/thedaviddias/Projects/frontendchecklist.io/packages/content/rules/en/security/csp.mdx). This appears to be a leftover development link from the author's local environment. While it reveals a local directory structure, it does not expose sensitive system credentials or user data.

avoid-eval