The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions found that attempt to override agent behavior, bypass safety guidelines, or extract system prompts.
[Data Exposure & Exfiltration] (SAFE): The skill focuses on documentation metrics. It does not access sensitive file paths (e.g., .ssh, .aws) or perform network operations to external domains.
[Remote Code Execution] (SAFE): There are no patterns involving the download or execution of remote scripts. The bash examples provided are intended for the agent's internal tool use (Grep).
[Obfuscation] (SAFE): No hidden content, Base64 encoding, or zero-width characters were found in the skill definition.
[Indirect Prompt Injection] (LOW): The skill ingests untrusted data by reading codebase files. While this is a known attack surface, the skill lacks high-risk write or network capabilities that could be exploited by embedded instructions in documentation.

analyzing-docs