The Agent Skills Directory

[SAFE]: The skill promotes security best practices for handling sensitive information in embedded systems development.
It encourages the use of template files (e.g., credentials.h.example) so that actual secrets are never committed to version control.
It automates the verification of .gitignore and pre-commit configurations to prevent the accidental exposure of private configuration files.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from the local file system.
Ingestion points: Uses Read, Grep, and Glob tools to scan source code and configuration files within a user-specified project path.
Boundary markers: Lacks explicit delimiters or instructions to treat ingested file content as non-executable data, which could allow malicious instructions embedded in project files to influence agent behavior.
Capability inventory: The skill possesses Write and Edit permissions, allowing it to modify the file system based on its analysis of the ingested data.
Sanitization: There is no evidence of sanitization or structural validation of the content read from files before it is processed by the logic that determines file modifications.

credential-setup