The Agent Skills Directory

[NO_CODE] (SAFE): This skill consists entirely of markdown instructions and does not include any scripts, executable code, or automated commands.
[EXTERNAL_DOWNLOADS] (SAFE): While the documentation mentions external tools like npm audit and snyk, the skill itself does not perform any downloads or network requests.
[PROMPT_INJECTION] (SAFE): No malicious instructions or bypass attempts were detected. The guidelines follow standard security auditing frameworks.
[DATA_EXFILTRATION] (SAFE): No network operations or sensitive file access patterns were identified.
[INDIRECT_PROMPT_INJECTION] (SAFE): While the skill is designed to process untrusted data (code to be audited), it possesses no harmful capabilities like command execution or file writing, mitigating the risk of downstream exploitation.

security-audit