The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns or security risks were detected within the provided files.
[PROMPT_INJECTION] (SAFE): The instructions emphasize grounding the agent in specific domain knowledge (e.g., 'Ignore generic approaches if a specific pattern exists here'). These are standard grounding techniques and do not attempt to bypass core safety protocols or perform jailbreaks.
[DATA_EXFILTRATION] (SAFE): There are no indicators of network operations, hardcoded credentials, or access to sensitive local file paths.
[REMOTE_CODE_EXECUTION] (SAFE): The skill consists entirely of markdown documentation. It does not include any scripts, executable files, or package dependencies.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill defines an attack surface by ingesting user creative vision to generate prompts. However, it demonstrates high maturity by including explicit validation rules in 'references/validations.md' aimed at preventing the very vulnerabilities (like unsafe input concatenation) that lead to injection attacks.

prompt-engineering-creative