container-scan-trivy
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 shell commands using the
trivyCLI to perform image, filesystem, and configuration scans. - [INDIRECT_PROMPT_INJECTION]: The skill processes scan results from external, untrusted sources (container images or local filesystems) which could contain adversarial strings designed to influence the agent's behavior during the summarization phase.
- Ingestion points: Reads scan results from
trivy-results.jsongenerated by the scanner (SKILL.md). - Boundary markers: None identified. The instructions do not specify the use of delimiters or warnings to ignore instructions within the scan data.
- Capability inventory: The skill uses shell execution capabilities to run
trivy(SKILL.md). - Sanitization: None identified. The agent is instructed to parse and present the raw findings directly.
Audit Metadata