The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is configured to analyze and process Golang source code (**/*.go) and leverages tools like go and golangci-lint via shell commands. This creates a surface for indirect prompt injection where maliciously crafted code, comments, or project configurations could attempt to influence the agent's reasoning or exploit the analysis tools.
Ingestion points: The skill reads and analyzes all .go files in the project scope as defined in the paths metadata.
Boundary markers: There are no explicit instructions or delimiters provided to help the agent distinguish between legitimate source code and potential malicious instructions embedded within the data it processes.
Capability inventory: The skill has permissions to execute commands via go, golangci-lint, and git using the allowed-tools restriction.
Sanitization: The skill does not define any validation or sanitization routines for the content of the files it reads before processing them with analysis tools.

golang-safety