latex-pdf-compiler
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
- COMMAND_EXECUTION (HIGH): The skill invokes
pdflatexto process user-provided or agent-generated LaTeX source. LaTeX distributions often allow shell escapes (using the\write18command) which enables the execution of arbitrary system commands. Even without explicit shell escape flags, many LaTeX environments allow reading sensitive system files using\inputor\read. - Evidence: SKILL.md specifies running
pdflatexwith the-interaction=nonstopmodeflag, but does not explicitly enforce-no-shell-escapeor other sandboxing constraints. - REMOTE_CODE_EXECUTION (HIGH): The skill relies on an external, unverifiable script
scripts/compile_latex.pyto perform the compilation logic. The content of this script is not included in the skill definition, making its security posture (such as input sanitization) impossible to verify. - Evidence: SKILL.md refers to
scripts/compile_latex.pyas the primary execution engine for compilation. - DYNAMIC_EXECUTION (MEDIUM): The skill performs runtime compilation of documents. While intended for LaTeX, the engine's capability to execute code or macros during the build process constitutes dynamic execution of potentially untrusted logic.
- INDIRECT_PROMPT_INJECTION (LOW): The skill creates a significant attack surface for indirect prompt injection. An attacker could provide malicious LaTeX code (e.g., in a document the user asks the agent to 'fix' or 'compile') containing instructions designed to exfiltrate data or manipulate the agent's behavior during the compilation process.
- Ingestion points:
SKILL.md(Workflow section) indicates the agent extracts LaTeX from artifacts provided in the conversation. - Boundary markers: None specified in the instructions to the agent; no explicit 'ignore embedded instructions' warnings are provided when passing data to the compiler.
- Capability inventory: Subprocess calls to
pdflatexand execution of a local Python script. - Sanitization: No evidence of LaTeX-specific sanitization or filtering of dangerous commands (like
\write18or\input) is present in the skill description.
Recommendations
- AI detected serious security threats
Audit Metadata