pli-migration-analyzer

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill is highly vulnerable to Category 8 attacks because it ingests untrusted external data and possesses significant execution capabilities.
  • Ingestion points: Reads and parses .pli, .PLI, and .pl1 source files from the workspace.
  • Boundary markers: Absent. There are no instructions or delimiters to help the agent distinguish between code to be analyzed and potential malicious instructions embedded in comments or strings.
  • Capability inventory: Executes local Python and Shell scripts, performs filesystem searches, and generates architectural design documents.
  • Sanitization: Absent. No logic is provided to filter or escape legacy code content before processing.
  • Command Execution (MEDIUM): The workflow relies on executing several local scripts (extract-structure.py, analyze-dependencies.sh, estimate-complexity.py, generate-java-classes.py) and shell commands (find). While these are functionally relevant, they represent a significant side-effect surface.
  • Unverifiable Dependencies (LOW): The skill references multiple external scripts and reference files (e.g., references/pli-reference.md, assets/migration-report-template.md) that are not included in the provided file, making a complete security audit of the execution logic impossible.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 10:24 AM