alera-agent-profiles
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the use of the
aleracommand-line tool for profile management. It includes commands for listing, creating, and updating configurations that can control agent behavior and sandboxing. - [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface by reading and processing data from external sources and existing profile descriptions.
- Ingestion points: Untrusted data enters via CLI commands that read the current catalog (
alera agent-profile list/show) and external model benchmarks (references/catalog-research.md). - Boundary markers: The skill mandates the use of specific, bounded prompts for smoke testing to prevent unintended actions during validation (
references/launch-validation.md). - Capability inventory: The skill possesses extensive capabilities through the
aleraCLI, including creating and launching agents with varying permission levels (references/maintenance.md). - Sanitization: No specific content sanitization or escaping mechanisms for external data are described.
Audit Metadata