skills/benjaroy/riff/sort/Gen Agent Trust Hub

sort

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The primary logic of the skill is restricted to text transformation and consolidation for organizational purposes.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted user input without utilizing isolation techniques.
  • Ingestion points: Raw notes, transcripts, and brainstorming fragments provided by users are processed as described in SKILL.md.
  • Boundary markers: There are no delimiters or explicit instructions used to wrap and isolate user-provided content from the agent's system prompt.
  • Capability inventory: The skill does not have access to any tools for file system modification, network communication, or administrative command execution.
  • Sanitization: No input validation or filtering is performed on the material before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 05:51 PM