trailsnap-ui-design
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: Hardcoded development environment credentials (
trailsnap/trailsnap) are provided inSKILL.mdfor accessing the local development environment.- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local PowerShell script for testing purposes:tests/scripts/run-tests.ps1.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project source code as part of its primary function, which represents a known attack surface. - Ingestion points: Reading source files from
package/website/src/**/*,AGENTS.md, and references within the workspace. - Boundary markers: No explicit delimiters or instructions to ignore embedded AI instructions within project source code are present.
- Capability inventory: Modifying code across the application and executing local shell scripts (
pwsh). - Sanitization: No sanitization or filtering of external source code content is mentioned before it is processed by the agent.
Audit Metadata