codeguard-css
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs shell command execution via
npxto run Stylelint diagnostics and formatting. It mitigates potential risks by using the--no-installflag during probe and linting stages (Step 3 and Step 4), ensuring that the agent only uses tools already present in the environment. - [INDIRECT_PROMPT_INJECTION]: The skill reads and processes CSS, SCSS, Sass, and LESS files, which establishes a surface for indirect prompt injection attacks where malicious code comments could attempt to influence the agent's logic.
- Ingestion points: Local project files with
.css,.scss,.sass, and.lessextensions, as specified inSKILL.mdandreferences/tooling/toolchain.md. - Boundary markers: The skill does not implement explicit delimiters or instructions to treat ingested file content as untrusted data that should not be followed as instructions.
- Capability inventory: The skill has the capability to execute shell commands (
npx) and read project configuration files. - Sanitization: No specific sanitization or filtering of the external tool output is defined before the results are reported back to the agent.
Audit Metadata