prompt
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided content to generate prompts, which creates a surface for indirect prompt injection.
- Ingestion points: The skill accepts 'pasted material' and user-defined tasks in SKILL.md to produce prompt text.
- Boundary markers: The skill includes explicit instructions to use delimiters like
<input>...</input>for pasted material in the workflow and guardrails sections. - Capability inventory: The skill utilizes file system write capabilities to create prompt records in the
docs/prompts/directory. - Sanitization: The skill focuses on delimitation as the primary method of separating user input from generated instructions, but lacks strict validation or sanitization of the content before it is written to the file system.
Audit Metadata