literature-review
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: A comprehensive analysis of the skill's instructions found no evidence of malicious intent, hidden commands, or deceptive practices. The content is strictly limited to guidance on conducting systematic literature reviews using academic frameworks.
- [NO_CODE]: The skill consists entirely of markdown documentation. It does not include any Python or Node.js scripts, binary executables, or command-line instructions.
- [PROMPT_INJECTION]: The skill defines a workflow for ingesting data from external academic sources, which constitutes a surface for indirect prompt injection.
- Ingestion points: External research papers and metadata retrieved from databases such as arXiv, Semantic Scholar, and ACM Digital Library (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or boundary markers when processing external text.
- Capability inventory: The skill does not provide or request any executable code capabilities or file-system access tools.
- Sanitization: The workflow does not explicitly describe methods for sanitizing or filtering text content from analyzed papers to prevent instruction leakage.
Audit Metadata