halo-asset-context

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_&_EXFILTRATION]: The skill requires sensitive credentials (HALO_CLIENT_ID, HALO_CLIENT_SECRET) to authenticate with the Halo REST API. The instructions correctly direct the use of environment variables for these secrets, which is a standard and secure practice for secret management.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection attacks because it processes untrusted data from an external system.
  • Ingestion points: External data enters the agent context via halo_get_asset and halo_get_asset_tickets, which fetch asset details and ticket descriptions from the Halo REST API (specified in SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or instructions to the agent to disregard embedded directives within the retrieved ticket data.
  • Capability inventory: The skill uses a Python-based MCP server (mcp-servers/halo-mcp/halo_mcp_server.py) to execute queries. While this skill is documented as read-only, it explicitly integrates with halo-change-request, which possesses write capabilities in the target environment.
  • Sanitization: There is no evidence of data sanitization or filtering of the content retrieved from the Halo API before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:29 PM
Security Audit — agent-trust-hub — halo-asset-context