surf-sdp-helm-flux

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a knowledge base and utility collection for developers working on the SURF SDP platform. The instructions and scripts are consistent with legitimate platform operations and contain no malicious intent or suspicious patterns.
  • [COMMAND_EXECUTION]: Several bash scripts (check-oci-tag.sh, force-reconcile.sh, and hr-status.sh) are included to help users interact with their Kubernetes clusters. These scripts use standard, well-known tools like kubectl, helm, and flux to perform read-only diagnostics or trigger standard resource reconciliations.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze logs and deployment outputs provided by users in a troubleshooting context. 1. Ingestion points: User-provided pipeline logs and kubectl command output (referenced in SKILL.md). 2. Boundary markers: The skill does not define specific delimiters for these inputs. 3. Capability inventory: The skill includes shell scripts for interacting with the Kubernetes API via kubectl, helm, and flux. 4. Sanitization: No specific input sanitization is implemented for the analyzed logs. The finding is assessed as safe because the skill is a reference tool for the agent and does not automate high-privilege actions based on external input.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 11:09 AM