proof-checker
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted LaTeX proof files and interpolates their content directly into prompts for reasoning models (e.g., Phase 1 review). It possesses write and execute capabilities that could be targeted by instructions embedded within the LaTeX data.
- Ingestion points: Reads
.texfiles and proof descriptions during Phase 0 and Phase 1. - Boundary markers: The LaTeX content is interpolated into the reviewer prompt (
[FULL PROOF CONTENT HERE]) without explicit protective delimiters or instructions to ignore embedded commands. - Capability inventory: The skill uses
Bash,Write,Edit, andAgenttools across its workflow. - Sanitization: No explicit sanitization or filtering of external LaTeX content is performed before processing.
- [COMMAND_EXECUTION]: The skill executes local system commands for document compilation and environment management.
- Evidence: Uses
pdflatex -interaction=nonstopmodeto compile audit reports and shell snippets to resolve the path forresearch_wiki.pyusinggit,awk, andpython3. These operations are consistent with the stated purpose of mathematical document auditing.
Audit Metadata