misconfig
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes established external security scanners (checkov, tfsec, kics, trivy, and semgrep) using shell commands in
SKILL.md(Step 3). These operations are restricted to standard security tools and are consistent with the skill's primary purpose. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted configuration and infrastructure data from the project being audited, which creates a surface for indirect prompt injection attacks.
- Ingestion points: In
SKILL.md(Step 1), the skill identifies and reads various project files, including environment files (*.env), YAML configurations, and infrastructure-as-code manifests. - Boundary markers: The instructions do not define clear delimiters or provide the agent with specific guidance to ignore natural language instructions that might be embedded within the audited configuration files.
- Capability inventory: The skill possesses the ability to execute shell commands (for scanning) and read files throughout the project scope.
- Sanitization: No sanitization or filtering of the analyzed file content is performed before the data is presented to the LLM for analysis in Step 4.
Audit Metadata