comply
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for downloading the 'conftest' utility from the official Open Policy Agent (OPA) GitHub repository to enable automated policy-as-code verification.
- [COMMAND_EXECUTION]: Documentation within the skill includes example shell scripts for setting up compliance tools, which include commands for downloading archives and performing privileged file operations to install binaries into system paths.
- [PROMPT_INJECTION]: The skill exhibits an inherent surface for indirect prompt injection due to its core function of ingesting and analyzing untrusted external artifacts such as codebase files, infrastructure configurations, and audit evidence.
- Ingestion points: Codebase source files, configuration files (Terraform, Kubernetes YAML), and evidence artifacts processed during the 'ASSESS' and 'MAP' phases in SKILL.md.
- Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded commands within the analyzed data.
- Capability inventory: The agent performs file system reads to assess controls and generates detailed compliance reports based on those assessments.
- Sanitization: There is no evidence of sanitization or strict validation of the content being analyzed for compliance.
Audit Metadata