kill-argument

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted document content (LaTeX, BibTeX, and PDF files) provided in the target directory. This content is passed to model-based review tools (Codex MCP) without sanitization or boundary markers, allowing malicious instructions embedded in a paper to potentially influence the agent's behavior.
  • Ingestion points: All LaTeX source files, bib files, and PDFs found within the directory provided via $ARGUMENTS (SKILL.md, Step 1).
  • Boundary markers: Absent. The content is interpolated into prompts without delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill utilizes Bash, Read, Write, and Edit tools, as well as multiple MCP review tools for analysis and adjudication.
  • Sanitization: No sanitization or filtering is performed on the content of the ingested files before they are sent to the model.
  • [COMMAND_EXECUTION]: The skill uses Bash(*) to execute file discovery commands. The use of $ARGUMENTS to define the working directory (PAPER_DIR="$ARGUMENTS") introduces a potential command injection surface if the input is not properly sanitized by the underlying platform before being executed in a shell environment.
  • Evidence: The script in Step 1 of the workflow directly assigns the user-provided $ARGUMENTS to a variable and uses it in a cd command.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 03:08 AM