The Agent Skills Directory

[COMMAND_EXECUTION]: The Python script scripts/agent.py executes the trivy command-line tool to perform security scans. The implementation correctly uses subprocess.run with a list of arguments rather than a single string, which is the recommended best practice to prevent shell injection vulnerabilities.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from scanned container images and filesystems, creating a potential surface for indirect injection if the scanner output is treated as instructions by a downstream agent. * Ingestion points: Untrusted data enters the agent context through the JSON results generated by the trivy CLI in scripts/agent.py. * Boundary markers: The script does not utilize explicit boundary markers or instructions to ignore embedded content within the tool's output. * Capability inventory: The skill possesses the capability to execute shell commands (via trivy) and write results to the local filesystem in scripts/agent.py. * Sanitization: The script performs standard JSON parsing of tool output but does not include specific sanitization or filtering of the findings content.
[EXTERNAL_DOWNLOADS]: The references/api-reference.md file points to the official Aqua Security Trivy documentation and GitHub repository. These are well-known, trusted sources for security tooling, and the skill does not perform any unverified or hidden remote downloads.

performing-container-security-scanning-with-trivy