review-game
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill analyzes untrusted source code from a directory provided via the $ARGUMENTS variable. This creates a surface for indirect prompt injection where instructions embedded in the analyzed code (such as comments or README files) could influence the agent's behavior during the review process.\n
- Ingestion points: The agent is instructed to read
package.json,index.html, and game entry points from the target directory (SKILL.md).\n - Boundary markers: The instructions do not define explicit delimiters or 'ignore embedded instructions' warnings for the analyzed content.\n
- Capability inventory: The skill involves reading and identifying code patterns, though it is explicitly restricted to read-only analysis.\n
- Sanitization: No sanitization or validation of the ingested code content is performed before processing.
Audit Metadata