volcengine-compliance
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a Python script (scripts/compliance.py) to execute the Volcengine CLI (ve) for auditing and compliance tasks. This is the primary function of the skill and is implemented securely using argument lists in subprocess.run to prevent shell injection vulnerabilities.
- [EXTERNAL_DOWNLOADS]: The skill setup requires the official @volcengine/cli package from the NPM registry. This is a trusted vendor resource provided by the author to enable core functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill processes cloud resource configurations and user requirements to generate compliance reports and custom Rego rules. This data ingestion surface is handled with appropriate security controls:
- Ingestion points: Untrusted resource configuration data enters via scripts/compliance.py (CLI output) and user-supplied requirements in SKILL.md.
- Boundary markers: Mandatory confirmation logic is present; the skill requires the --confirm flag and explicit user consent for any operations that change the account state.
- Capability inventory: The skill performs subprocess calls to the ve CLI and writes local report artifacts in scripts/compliance.py.
- Sanitization: Payloads passed to the CLI are structured and sanitized through JSON encoding.
Audit Metadata