audit
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external frontend code (HTML, CSS, JavaScript) to perform technical audits. This creates a surface where malicious instructions embedded in code comments or metadata of the audited project could potentially influence the agent's behavior during the audit process.
- Ingestion points: Processes user-provided code snippets or files representing frontend components, pages, or features for analysis.
- Boundary markers: The instructions do not specify explicit delimiters or warnings to ignore instructions embedded within the data being audited.
- Capability inventory: The skill is limited to generating text-based audit reports and does not possess capabilities for file writing, network operations, or shell command execution.
- Sanitization: No explicit sanitization or escaping of the audited content is described in the prompt logic.
- [SAFE]: The skill's logic is purely analytical and instructional. It focuses on identifying technical debt and accessibility issues without requesting sensitive permissions or performing hidden operations. All recommended commands (e.g., /optimize, /adapt, /polish) are internal references to other intended agent skills.
Audit Metadata