contract-cli-mdm-fields
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied arguments for CLI commands including --biz-line, --profile, and --user-id flags found in SKILL.md and reference files (Ingestion points). No delimiters or boundary markers are established to isolate user input (Boundary markers absent). The agent executes these inputs using the contract-cli tool (Capability: command execution). Documentation states that common query parameters are passed through without local validation (Sanitization absent).
- [SAFE]: No patterns of data exfiltration, credential exposure, or remote code execution were detected. Internal source code references are provided for context and do not facilitate unauthorized system access.
Audit Metadata