interf-preview

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes data from an external file (interf.yaml) to generate its output report.
  • Ingestion points: Reads interf.yaml from the project root.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided when processing the file content.
  • Capability inventory: The skill has the capability to write files to the local file system (saving results to .interf/previews/).
  • Sanitization: No evidence of sanitization or validation of the input file content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 12:25 AM