scaffold-component-olm

Warn

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interpolates user-supplied strings (component-name and package) directly into bash commands in Step 1 (oc get packagemanifest <package>) and Step 4 (kustomize build components/<component-name>/). This pattern is susceptible to command injection if the input contains shell metacharacters (e.g., ;, &, |), allowing for arbitrary command execution within the agent's context.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. 1. Ingestion points: $ARGUMENTS and user input for component/package configuration. 2. Boundary markers: Absent. 3. Capability inventory: Bash, Write, and Read tools. 4. Sanitization: Absent. Malicious input could be used to manipulate generated manifests or influence tool execution logic.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 19, 2026, 01:10 AM
Security Audit — agent-trust-hub — scaffold-component-olm