skills/octavehq/lfgtm/train/Gen Agent Trust Hub

train

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection.
  • Ingestion points: It fetches content from the GTM library and conversation findings using tools like list_findings, get_event_detail, search_knowledge_base, and get_playbook (File: SKILL.md).
  • Boundary markers: The instructions do not define clear delimiters or "ignore instructions" warnings when interpolating fetched data into the role-play or quiz prompts.
  • Capability inventory: The agent has access to various library management tools and can generate content based on fetched data.
  • Sanitization: There is no evidence of sanitization or validation of the content retrieved from the external data sources before it is presented or used to drive the agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 03:09 AM