cost-booster-route
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted data from user inputs and memory search. This content is classified into routing tiers for cost reporting.
- Ingestion points: User-provided task descriptions and history from memory_search in SKILL.md.
- Boundary markers: Absent.
- Capability inventory: Bash execution, memory_store calls, and hooks_route classification.
- Sanitization: Absent.
- [COMMAND_EXECUTION]: Instructs the agent to run a Bash command (memory_store) to persist metrics. The command uses shell interpolation for timestamps and numeric values for counts, which follows standard operational patterns for the platform.
Audit Metadata