web-design-guidelines

Sanitize or validate all external inputs (file contents, API responses, user messages) before including them in prompts or tool calls. Implement input/output boundaries between trusted and untrusted data.

Likely FP if the matched text is the skill's own instruction set describing how to handle user input, not an actual injection payload.

Sanitize or validate all external inputs (file contents, API responses, user messages) before including them in prompts or tool calls. Implement input/output boundaries between trusted and untrusted data.

Likely FP if the matched text is the skill's own instruction set describing how to handle user input, not an actual injection payload.

Sanitize or validate all external inputs (file contents, API responses, user messages) before including them in prompts or tool calls. Implement input/output boundaries between trusted and untrusted data.

Likely FP if the matched text is the skill's own instruction set describing how to handle user input, not an actual injection payload.

Sanitize or validate all external inputs (file contents, API responses, user messages) before including them in prompts or tool calls. Implement input/output boundaries between trusted and untrusted data.

Likely FP if the matched text is the skill's own instruction set describing how to handle user input, not an actual injection payload.

Pin the SDK or script to a specific version and verify its checksum after download. Prefer installing SDKs via a package manager instead of fetching remote scripts directly.

Likely FP if the match is documentation showing how to install an official SDK (e.g., Google Cloud SDK, AWS CLI) from its canonical URL.

Replace GitHub raw.githubusercontent.com references with pinned commit SHAs instead of branch names (e.g., /commit-sha/file instead of /main/file). Branch references are mutable.

Likely FP if the raw GitHub URL points to a versioned release tag in a well-known repository, though even tags are technically mutable.