agent-challenges
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it is designed to ingest and process user-supplied code for validation.
- Ingestion points: The
solution_codeparameter in themcp__flow-nexus__challenge_submittool, which receives data from users. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from being influenced by instructions embedded within the user's solution code.
- Capability inventory: The skill has the capability to invoke multiple MCP tools (
mcp__flow-nexus__challenges_list,mcp__flow-nexus__challenge_submit,mcp__flow-nexus__achievements_list,mcp__flow-nexus__leaderboard_get) to interact with the platform's backend. - Sanitization: The instructions do not specify any validation or sanitization steps for the input code before it is passed to the submission tool.
Audit Metadata