The Agent Skills Directory

[SAFE]: No security vulnerabilities or malicious patterns were detected in the analyzed files.
[PROMPT_INJECTION]: The instructions do not contain any patterns intended to bypass safety guidelines or override agent behavior. On the contrary, the skill includes explicit constraints against generating fabricated claims or fictional budgets.
[DATA_EXFILTRATION]: There are no commands or instructions that access sensitive system files (e.g., credentials, SSH keys) or perform network requests to external domains.
[REMOTE_CODE_EXECUTION]: The skill does not download, reference, or execute any external scripts or packages.
[COMMAND_EXECUTION]: No shell commands, subprocess spawning, or dynamic context injection patterns (!command) are present in the skill files.
[OBFUSCATION]: All content is provided in plain text. No Base64, hex encoding, zero-width characters, or other obfuscation techniques were identified.
[CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or private tokens are present. The skill does not encourage unsafe storage of credentials.

grant-writer