ng-styling
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project source code files that could contain malicious instructions designed to manipulate the agent's audit or fix logic during execution.
- Ingestion points: The agent reads and analyzes component stylesheets (.scss), templates (.html), and TypeScript files (*.ts) as described in the Workflow section of SKILL.md.
- Boundary markers: The skill does not instruct the agent to use specific delimiters or include "ignore embedded instructions" warnings when processing these source files, leaving it vulnerable to instructions hidden in code comments.
- Capability inventory: The skill has read/write access to project files (on approval) and executes local shell commands via pnpm (build, lint, test) to verify changes, providing a potentially exploitable execution path if the agent is successfully injected.
- Sanitization: There is no evidence of sanitization, escaping, or filtering of the source code content before it is interpolated into the agent's reasoning context.
Audit Metadata