abel
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a Python script (
graph_probe.py) to verify the user's authentication status. This script is part of the 'abel-ai-lab' vendor ecosystem and is accessed via a path relative to the skill installation directory. - [INDIRECT_PROMPT_INJECTION]: The skill ingests natural language user queries to determine which sub-skill to invoke.
- Ingestion points: User queries regarding investment, trading, or general analysis are processed as input for routing logic.
- Boundary markers: No explicit boundary markers or 'ignore' instructions are provided to the agent to prevent embedded instructions within the user query from influencing the routing decision.
- Capability inventory: The skill has the capability to execute shell commands via
python3and transition the agent's context to other powerful skills (abel-auth,abel-invest,abel-ask). - Sanitization: There is no evidence of input sanitization or validation of the user's query before it is evaluated for routing purposes.
Audit Metadata