website-infra
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to execute AWS CLI commands and run local scripts likevalidate-stack.shto manage infrastructure stacks. - [PROMPT_INJECTION]: The skill ingests parameters from a local
site-config.jsonfile to populate shell commands, creating a potential surface for indirect prompt injection. \n - Ingestion points:
site-config.json(SKILL.md) \n - Boundary markers: None present \n
- Capability inventory: Shell command execution via
aws cloudformationand local scripts (SKILL.md) \n - Sanitization: No explicit sanitization or validation of the configuration values before shell interpolation is described.
Audit Metadata