manuscript-typography
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, which creates a surface for indirect prompt injection if malicious instructions are embedded within the documents being audited.
- Ingestion points: The workflow requires reading all project LaTeX files (
.tex) and the build log (.log) to identify typographic errors and overfull boxes (described in Step 1 and Pass 9.5 ofSKILL.md). - Boundary markers: The instructions do not specify the use of delimiters, XML tags, or "ignore instructions" warnings to isolate the untrusted manuscript content from the agent's internal reasoning.
- Capability inventory: The skill utilizes file system access and shell commands (specifically
grep) to process the external data, creating a potential path for data-driven influence over agent actions. - Sanitization: No sanitization or validation of the input file content is implemented before the data is presented to the model for analysis.
Audit Metadata