conversation-to-document

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill contains no executable code or external dependencies. It focuses exclusively on providing natural language instructions for text transformation.
  • [NO_CODE]: No scripts or binaries are distributed with the skill. All logic is contained in Markdown and YAML configuration files.
  • [PROMPT_INJECTION]: The skill processes external transcript data, which represents an indirect prompt injection surface. However, the risk is negligible as the skill lacks side effects or tool usage.
  • Ingestion points: Chat transcripts (SKILL.md, agents/openai.yaml)
  • Boundary markers: Absent; the instructions do not specify delimiters for the transcript content.
  • Capability inventory: None; the skill does not request or use any tools (e.g., shell, network).
  • Sanitization: Absent; no filtering or validation logic is applied to the processed text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 09:05 AM
Security Audit — agent-trust-hub — conversation-to-document