prompt-library
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill manages a library of 2,500+ prompts which could contain malicious instructions.
- Ingestion points: Data is read from JSON files in
{PROMPT_ENGINE_DIR}/prompts/. - Boundary markers: No delimiters are specified to isolate prompt content from the agent's instructions.
- Capability inventory: The agent executes shell-based Python scripts to interact with the data.
- Sanitization: No validation or sanitization of the prompt content is defined.
- [COMMAND_EXECUTION]: Shell commands in the skill use placeholders like
CATEGORYandMODELwhich are populated by user input. This creates a risk of command injection if the agent does not sanitize these inputs before execution.
Audit Metadata