crypto-bot-management
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a potential surface for indirect prompt injection as it ingests and processes external bot data (status, analytics, positions) from the Traderton platform, which could theoretically contain instructions intended to influence the agent's logic.\n
- Ingestion points: Tools such as
list_bots,get_bot_status,get_analytics, andlist_positions(as described in SKILL.md) ingest external data into the agent context.\n - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the tool definitions.\n
- Capability inventory: The skill can perform state-changing operations via
create_bot,start_bot,stop_bot, andadjust_bot_config.\n - Sanitization: No sanitization or validation logic is specified for the data retrieved from the platform.\n- [SAFE]: The skill consists solely of instructions for tool usage. It does not include executable scripts, obfuscated content, hardcoded credentials, or unauthorized network operations. The tools and platform described align with the stated purpose of the skill.
Audit Metadata