The Agent Skills Directory

[PROMPT_INJECTION]: No instructions were found that attempt to override agent behavior, bypass safety guidelines, or reveal system prompts.
[DATA_EXFILTRATION]: No network operations (curl, wget, fetch) or access to sensitive local file paths (~/.ssh, ~/.aws, .env) were detected.
[OBFUSCATION]: The content was analyzed for Base64, zero-width characters, homoglyphs, and hex escapes; no obfuscation techniques were found.
[REMOTE_CODE_EXECUTION]: The skill does not contain any package installations, remote script downloads, or dynamic execution patterns.
[DYNAMIC_CONTEXT_INJECTION]: There are no instances of the !command syntax used for pre-execution shell command injection.
[INDIRECT_PROMPT_INJECTION]: The skill primarily provides guidance based on direct user conversation and does not ingest data from untrusted external sources (APIs, web pages) that could contain hidden instructions.

ai-pricing