acs-catalysis
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill contains purely instructional content related to academic publishing and journal selection criteria. No malicious patterns such as prompt injection, obfuscation, or persistence mechanisms were detected.
- [NO_CODE]: There is no executable code, scripts, or package dependencies included in the skill. The instructions are entirely text-based for the purpose of guiding an AI's evaluation of a manuscript.
- [DATA_EXPOSURE]: The skill references local resource files (e.g.,
../../resources/source-basis.md) for internal logic. These are standard path references for agent-integrated knowledge bases and do not represent an attempt to exfiltrate sensitive user data. - [INDIRECT_PROMPT_INJECTION]: While the skill is intended to process external manuscript data, it possesses no dangerous capabilities such as network requests, file-system writes, or command execution that could be exploited by malicious content within a manuscript.
Audit Metadata