resubmit-pipeline

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted reviewer reports provided by the user, which serves as a potential vector for instructions hidden in data to influence the agent's behavior during the automated improvement phase.
  • Ingestion points: Reviewer reports are read from the external directory provided via the --review-corpus argument in Phase 1.
  • Boundary markers: Content is atomized into a structured KNOWN_WEAKNESSES.md file, but the instructions do not specify the use of strict delimiters (e.g., XML tags or unique separators) or 'ignore embedded instructions' warnings when this text is interpolated into LLM prompts.
  • Capability inventory: The skill has access to Bash(*), Write, and Edit tools, and it orchestrates other powerful skills capable of modifying the local filesystem.
  • Sanitization: The skill does not describe any specific sanitization or filtering logic to strip potentially malicious prompt injection strings from the reports before they are processed.
  • [COMMAND_EXECUTION]: The skill uses shell commands for project management, directory setup, and health checks.
  • Evidence: Phase 0 utilizes mkdir, cp, and rsync to create isolated environments for new venues, ensuring prior submissions are not modified.
  • Evidence: Phase 0.5 executes pdfinfo and awk to measure page counts and grep for anonymity scanning across multiple layers.
  • [DYNAMIC_EXECUTION]: The skill performs LaTeX compilation, which involves executing macros and can interact with the host system if not properly restricted.
  • Evidence: Phases 0.5 and 4 use latexmk -pdf -interaction=nonstopmode -halt-on-error main.tex to build the final document. This is the primary function of the skill and is documented as part of the intended workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 09:43 AM