prioritize-features

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill is composed entirely of natural language instructions and does not include any scripts, binaries, or executable code.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and process external data without explicit sanitization.
  • Ingestion points: The agent is instructed to read and analyze user-provided files such as spreadsheets, backlogs, and opportunity assessments.
  • Boundary markers: There are no explicit delimiters or 'ignore embedded instructions' warnings provided to distinguish user data from system instructions.
  • Capability inventory: The skill has the capability to generate and save output as markdown files on the local system.
  • Sanitization: No validation or sanitization steps are defined for the data extracted from user-provided files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 05:03 AM