systematic-review-lite
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of Markdown templates and guidelines for academic research. No executable scripts, binaries, or automated command execution patterns were found in any of the analyzed files.\n- [NO_CODE]: The skill provides procedural guidance and documentation rather than functional code, which significantly minimizes the potential attack surface.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied research questions and bibliographic citations. This creates an ingestion surface for untrusted data, but the lack of executable capabilities (tools, scripts, or subprocesses) within the skill itself renders this risk negligible.\n
- Ingestion points: User-provided research questions (PICO/PCC) and reference lists as described in
README.mdandSKILL.md.\n - Boundary markers: None explicitly defined in the markdown templates to distinguish user data from instructions.\n
- Capability inventory: No file system operations, network requests, or shell command executions are present in this skill.\n
- Sanitization: No input validation or escaping mechanisms are implemented.
Audit Metadata