behavioral-modes

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes operational modes that process external data without defining security delimiters, creating a vulnerability surface for indirect prompt injection.
  • Ingestion points: The agent is instructed to use Read, Glob, and Grep tools to ingest and analyze project files, logs, and user-provided code in several modes.
  • Boundary markers: No specific delimiters or instructions (e.g., 'treat the following as data only') are included to protect the agent from instructions embedded within analyzed files.
  • Capability inventory: The skill utilizes file system access tools (Read, Glob, Grep) to retrieve content from the environment.
  • Sanitization: There is no evidence of validation or filtering of external content before it is processed by the AI persona.
  • [NO_CODE]: The skill is composed entirely of markdown documentation and YAML configuration and does not include any scripts, binaries, or executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 08:35 AM