The Agent Skills Directory

COMMAND_EXECUTION (SAFE): The skill provides scripts (init_skill.ts and quick_validate.ts) that perform legitimate file system operations such as creating directories and writing template files. These operations are essential for the skill's primary purpose and do not exhibit malicious intent.- DATA_EXFILTRATION (SAFE): The analysis found no evidence of network requests or code designed to transmit sensitive data to external servers.- CREDENTIALS_UNSAFE (SAFE): No hardcoded API keys, tokens, or other sensitive credentials were found within the skill files.- PROMPT_INJECTION (SAFE): The instructions in SKILL.md are purely informational and do not attempt to override system prompts or bypass safety guardrails.- EXTERNAL_DOWNLOADS (SAFE): The skill uses the standard yaml package for parsing. No untrusted or suspicious remote scripts are downloaded or executed.

skill-creator