The Agent Skills Directory

[Prompt Injection] (SAFE): No patterns of instruction overrides, safety bypasses, or adversarial role-play were detected in the skill content.
[Data Exposure & Exfiltration] (SAFE): The skill does not contain hardcoded credentials, sensitive file paths, or network exfiltration logic.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): No external package managers or remote script download patterns (e.g., curl|bash) are present.
[Obfuscation] (SAFE): No encoded strings, zero-width characters, or homoglyphs were found in the metadata or body.
[Indirect Prompt Injection] (SAFE): While the skill defines a workflow that involves reading data, it provides no automated logic or interpolation code that could be exploited by malicious data inputs.

capacity-planning