deploy
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core workflow involves analyzing untrusted user codebases to generate infrastructure recommendations and deployment scripts.
- Ingestion points: The agent is instructed to scan the framework, database, and dependencies of any provided codebase (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters provided to isolate the untrusted codebase content from the agent's internal instructions.
- Capability inventory: The skill can generate Infrastructure-as-Code (IaC) and execute shell commands for scanning and deployment (SKILL.md, references/security.md).
- Sanitization: The skill mitigates this risk by requiring automated security scans (cfn-nag, checkov) and mandatory user confirmation before any deployment command is executed.
- [COMMAND_EXECUTION]: The skill workflow involves executing shell-based security tools and deployment commands. This behavior is intended, documented, and includes safety checkpoints such as user approval and pre-execution quality gates.
Audit Metadata