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

generate

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 because it processes data retrieved from external sources (e.g., person and company details) to generate content.
  • Ingestion points: Data entering through the find_person, find_company, and search_knowledge_base tools in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt templates.
  • Capability inventory: The skill can invoke generation tools like run_email_agent and generate_content, but it lacks access to the system shell or local file system.
  • Sanitization: There is no evidence of input validation or escaping for the data fetched from the knowledge base or person research tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 03:09 AM