asset-check
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository content (markup, source code) to identify and fix asset issues. This creates a surface where malicious instructions embedded in project files could attempt to influence agent actions during the modification phase.
- Ingestion points: Repository files including markup, component code, and UI strings (SKILL.md).
- Boundary markers: The skill explicitly instructs the agent to treat repository content as data rather than instructions (SKILL.md).
- Capability inventory: The skill has the capability to write to the file system to fix assets and uses screenshot tools and the Icons8 MCP.
- Sanitization: No active sanitization of code content is specified beyond the directive to ignore instructions in data.
Audit Metadata