The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions to override system prompts or bypass safety filters were found. The guidelines are strictly focused on technical writing style and documentation integrity.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network exfiltration patterns were detected. The skill explicitly instructs to cite authoritative sources and maintain information boundaries.
[Remote Code Execution] (SAFE): There are no patterns for downloading or executing remote scripts (e.g., curl | bash).
[Command Execution] (SAFE): While the skill provides formatting rules for bash and sh code blocks in documentation, it does not include commands for the agent to execute on the host system. It emphasizes providing read-only or --dry-run versions for safety.
[Obfuscation] (SAFE): No hidden or encoded content (Base64, zero-width characters, etc.) was identified in the instructions.
[Indirect Prompt Injection] (LOW): As a documentation tool, it ingests technical data. However, it includes safety-oriented instructions such as not adding unverified conclusions and confirming information with developers before publication.

tech-doc