The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard CLI commands for installing and running the Trivy security scanner, which is the primary and intended function of the skill.
[EXTERNAL_DOWNLOADS]: The skill references and pulls resources from trusted sources, including official GitHub Actions from Aqua Security and official Docker images, ensuring that the vulnerability scanning logic and databases are legitimate.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it is designed to analyze external, potentially untrusted container images, filesystems, and IaC configurations.
Ingestion points: Untrusted data enters the agent context through file and image scanning commands like trivy image and trivy fs in SKILL.md.
Boundary markers: The instructions do not explicitly define delimiters for tool output, but the use of structured formats like SARIF and JSON provides inherent data separation.
Capability inventory: The skill is capable of executing shell commands and pre-bundled Python scripts to process results and generate reports.
Sanitization: The skill relies on Trivy's structured parsing and reporting engines to sanitize and organize external data before it is presented to the user or agent.

sca-trivy