The Agent Skills Directory

[SAFE]: The skill is a purely instructional guide focused on defensive security practices and operational security (OPSEC) for researchers.
[DATA_EXPOSURE]: The skill provides explicit instructions on how to prevent accidental data exposure. It includes procedures for masking session cookies, PII (Personally Identifiable Information), and other sensitive metadata in evidence files.
[COMMAND_EXECUTION]: The skill includes benign shell functions (e.g., sanitize_har) using jq to process local HAR files. These commands are localized templates for the user to perform sanitization and do not involve remote code execution or suspicious subprocess spawning.
[PROMPT_INJECTION]: No prompt injection patterns, bypass markers, or attempts to override agent behavior were found. The instructional language is consistent with the stated purpose of professional reporting hygiene.
[REMOTE_CODE_EXECUTION]: The skill contains JavaScript snippets for use in browser DevTools. These snippets use standard APIs like fetch with credentials: 'include' to safely demonstrate vulnerabilities without hardcoding or echoing secrets. No remote scripts are downloaded or executed.

evidence-hygiene