The Agent Skills Directory

Indirect Prompt Injection (LOW): The skill is designed to ingest and analyze untrusted writing samples which could contain malicious instructions aimed at overriding the agent's behavior.
Ingestion points: User-provided writing samples (drafts, fragments) and existing files found via Grep or Glob.
Boundary markers: Absent. The skill does not define specific delimiters or instructions to ignore embedded commands within user samples.
Capability inventory: The skill uses Read, Grep, Glob, Write, and Edit to manage local project documentation.
Sanitization: Absent. Input content is not sanitized or validated before processing.
Data Exposure & Exfiltration (SAFE): No hardcoded credentials, sensitive file path access, or network operations were detected.
Unverifiable Dependencies & Remote Code Execution (SAFE): No external package installations or remote script executions (e.g., curl | bash) are present.

cw-voice