latex-manuscript-format-converter
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of manuscript drafts and journal template instructions (Ingestion points: manuscript source text and target template files). There are no specific instructions to use boundary markers or delimiters for this input (Boundary markers: absent). The skill has no capabilities to execute commands, write to the file system, or make network requests (Capability inventory: none). No sanitization routines are specified for the incoming manuscript text (Sanitization: absent).
- [INDIRECT_PROMPT_INJECTION]: The skill package includes an evaluation report file that contains self-referential safety assertions such as 'security: PASS'. Following the security audit protocol, these claims are treated as data to be evaluated and are not considered authoritative conclusions regarding the skill's safety (Category 8e).
Audit Metadata