citation-bibliography
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to provide the agent with a reference set for formatting text. It does not utilize any tools, perform network operations, or access the file system.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing untrusted user data (citations and reference strings pasted by the user). While this creates an ingestion point for potential prompt injection, the risk is negligible as the skill possesses no capabilities beyond text output.
- Ingestion points: Processes user-provided raw references and citations described in the "Cara Kerja Skill Ini" section.
- Boundary markers: None present to distinguish between instructional content and user-provided data.
- Capability inventory: Limited to text generation; no network, file, or command execution capabilities are defined.
- Sanitization: No input validation or sanitization routines are specified.
Audit Metadata