The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions designed to override agent behavior, bypass safety filters, or extract system prompts were found.
[Data Exposure & Exfiltration] (SAFE): The skill does not reference sensitive file paths, include hardcoded credentials, or perform network operations that could lead to data exfiltration.
[Obfuscation] (SAFE): No Base64 encoding, zero-width characters, homoglyphs, or other forms of hidden content were detected.
[Remote Code Execution] (SAFE): There are no commands to download external scripts or execute code from untrusted sources. No package manager files (e.g., package.json, requirements.txt) are present.
[Privilege Escalation & Persistence] (SAFE): No commands for elevating user privileges (e.g., sudo) or establishing persistence on the host system (e.g., crontabs, shell profile modifications) are included.
[Indirect Prompt Injection] (SAFE): While the skill involves processing user-provided objectives, it lacks any high-risk capabilities (like shell access or network requests) that could be exploited via malicious input.

Pinterest Strategist