cx-profiling
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
cxCLI to execute various profiling commands. All identified commands (e.g.,cx profiling services,cx profiling flame-graph) are read-only operations designed for telemetry and performance analysis. - [INDIRECT_PROMPT_INJECTION]: The skill handles data from external profiling APIs which represents an ingestion surface for untrusted content (such as function names or metadata labels).
- Ingestion points: Data is received from the output of
cx profilingcommands. - Boundary markers: None present; the skill does not explicitly instruct the agent to ignore potential instructions embedded in the profiling data.
- Capability inventory: The skill executes shell-based CLI commands for querying data.
- Sanitization: No explicit sanitization or escaping of the tool output is documented.
Audit Metadata