The Agent Skills Directory

[PROMPT_INJECTION] (SAFE): No patterns were detected that attempt to override system instructions or bypass safety filters. The documentation uses natural instructional language for software development best practices.
[DATA_EXFILTRATION] (SAFE): No network operations or sensitive file access patterns were found. The code snippets provided are conceptual and for documentation purposes.
[REMOTE_CODE_EXECUTION] (SAFE): No remote scripts, package installations, or dynamic execution patterns (like eval or subprocess calls) are present.
[CREDENTIALS_UNSAFE] (SAFE): No hardcoded API keys, secrets, or tokens were detected. The snippets use placeholders and schema definitions.
[OBFUSCATION] (SAFE): No Base64, zero-width characters, or homoglyphs were identified in the content.
[INDIRECT_PROMPT_INJECTION] (SAFE): While the skill processes user-facing language patterns, it does not ingest untrusted data at runtime or feed it into a decision-making pipeline that would create an injection surface.

design-justice