create-skill-from-workflow
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests conversation history to generate a new SKILL.md file, which can lead to the persistence of malicious instructions if the original workflow was compromised.
- Ingestion points: The skill instructs the agent to review the current conversation history to identify steps and tools used (SKILL.md, Step 1).
- Boundary markers: The template provided for the new skill does not include boundary markers or instructions for the agent to ignore embedded commands within the processed text.
- Capability inventory: The skill utilizes file-writing capabilities to save the new skill to the filesystem in the .claude/skills/ directory (SKILL.md, Step 4).
- Sanitization: There is no explicit requirement for sanitizing or escaping content extracted from the conversation history before it is written into the new skill file.
Audit Metadata