The Agent Skills Directory

[No Executable Code] (SAFE): Analysis of the 12 files confirms the skill is composed entirely of Markdown documentation. No scripts (.py, .js, .sh), configuration files, or binaries are present.
[Indirect Prompt Injection] (INFO): The skill's function is to analyze untrusted Go source code. 1. Ingestion points: External Go files and pull request descriptions. 2. Boundary markers: None defined within the skill. 3. Capability inventory: The skill possesses no executable code or tools with network, file system, or command execution capabilities. 4. Sanitization: None defined. The risk is limited to potential bias in the agent's reasoning output when analyzing malicious source code.

go-review