submission-prep

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script (scripts/render.sh) to render the manuscript as part of its automated workflow.
  • [PROMPT_INJECTION]: The skill processes untrusted content from external manuscript files (index.qmd, references.bib) and notebook files, which constitutes an indirect prompt injection attack surface.
  • Ingestion points: Data is read from index.qmd, references.bib, and various Jupyter notebook files referenced in the manuscript.
  • Boundary markers: The instructions do not specify any delimiters or ignore-instructions to isolate the manuscript text from the agent's logic.
  • Capability inventory: The agent has access to shell execution (Bash), file manipulation (Write, Edit), and file system traversal (Glob).
  • Sanitization: There is no evidence of sanitization or escaping of the content read from the manuscript files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 10:10 AM
Security Audit — agent-trust-hub — submission-prep