llm-application-dev-ai-assistant
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as an informational resource providing best practices and code templates for building conversational AI. It does not include any executable scripts, binaries, or configuration that would permit unauthorized file access, network operations, or command execution within the agent's environment.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input through the
$ARGUMENTSparameter in both the main skill file and the implementation playbook. - Ingestion points: The
$ARGUMENTSvariable is interpolated into the Requirements section ofSKILL.mdandresources/implementation-playbook.md. - Boundary markers: No delimiters or instructions to ignore embedded commands are present around the interpolated input.
- Capability inventory: The skill does not request or use any tools, file-system writing capabilities, or network access.
- Sanitization: There is no evidence of input validation or sanitization of the user-provided arguments.
- Although a vulnerability surface exists, the lack of dangerous capabilities prevents this from being exploitable.
Audit Metadata