The Agent Skills Directory

Prompt Injection (SAFE): The skill instructions are focused on writing style and do not contain attempts to bypass safety filters or override agent constraints.
Data Exposure & Exfiltration (SAFE): No sensitive file paths, hardcoded credentials, or network requests were detected. The skill works entirely within the agent's text-processing context.
Obfuscation (SAFE): No Base64, zero-width characters, or other encoding techniques intended to hide malicious content were found.
Unverifiable Dependencies & Remote Code Execution (SAFE): The skill does not define any external packages or attempt to download/execute remote scripts.
Indirect Prompt Injection (LOW): The skill is designed to ingest and process untrusted text provided by users for 'humanization' and has access to file system modification tools.
Ingestion points: Text provided by the user via natural language prompts (SKILL.md).
Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' warnings for the input text.
Capability inventory: The skill is allowed to use Read, Write, Edit, Grep, and Glob tools.
Sanitization: No sanitization or validation of the input text is performed before processing.

humanizer