container-scan-dockle
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the
docklecommand-line utility to perform security audits on container images. The results are output to a JSON file for analysis. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external container images that may contain attacker-controlled content in metadata, labels, or environment variables.
- Ingestion points: The agent parses the
dockle-results.jsonfile produced by the scan inSKILL.md. - Boundary markers: There are no explicit delimiters or instructions to ignore potential injection strings within the JSON results.
- Capability inventory: The skill has the ability to execute shell commands (
dockle) and read local files. - Sanitization: No sanitization or validation of the tool's output is performed before it is processed by the agent.
Audit Metadata