learn
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by processing untrusted data to generate agent instructions.
- Ingestion points: The skill gathers material from local directories, files, URLs, and conversation history.
- Boundary markers: There are no instructions to use delimiters or ignore instructions found within the source material.
- Capability inventory: The agent has access to file-reading tools, web-browsing tools, and file-writing tools to save skills to the local system.
- Sanitization: No sanitization or validation of the ingested content is specified before drafting the new skill file.
- [COMMAND_EXECUTION]: The README suggests an installation command using
npx, which executes code from the vendor's repository.
Audit Metadata