secdevai-oci-image-security
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists exclusively of instructional documentation and reference materials. No executable code, scripts, or obfuscated payloads are included in the package.
- [INDIRECT_PROMPT_INJECTION]: As a security analysis tool, the skill is designed to ingest and process data from external, untrusted sources such as container images and scanner reports. While no malicious instructions were detected within the skill itself, processing untrusted data is a inherent attack surface for AI agents.
- Ingestion points: The skill instructs the agent to read and analyze contents of container images, including configuration files, environment variables, and metadata, as well as outputs from vulnerability scanners like Trivy and Grype.
- Boundary markers: The skill suggests a structured markdown format for outputting findings but does not provide explicit delimiters or 'ignore' instructions for the data being analyzed.
- Capability inventory: The instructions require the agent to execute local shell commands (e.g.,
grep,find,strings,ldd) and run external security scanning tools. - Sanitization: No explicit sanitization steps are defined for the data processed from the target images.
Audit Metadata