performance-expert
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from local JSON audit files (
bundle.json,lighthouse.json,deps.json,similarity.json) which serves as an ingestion point for external data. - Ingestion points: Reads multiple JSON reports from the
.frontend-review/report/latest/raw/directory (SKILL.md). - Boundary markers: There are no specific delimiters or instructions provided to the agent to distinguish between the report data and system instructions.
- Capability inventory: The skill involves reading local project files and writing a new markdown report to the repository filesystem.
- Sanitization: The instructions do not specify any validation or sanitization steps for the data extracted from the JSON reports before it is included in the output summary.
Audit Metadata