academic
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads project-specific configuration files such as .claude/CLAUDE.md and local agent definitions in .claude/agents/.md and incorporates their content into prompts for subagents. -- Ingestion points: .claude/CLAUDE.md, .claude/agents/.md, and user-provided academic files. -- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within these files. -- Capability inventory: The orchestrator and its subagents have access to Bash, Write, Edit, and Agent tools. -- Sanitization: No explicit sanitization or validation of the content from these local project files is performed before interpolation into prompts.
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform academic tasks like LaTeX layout auditing or bibliography management. While consistent with the stated purpose, this provides a powerful capability that could be abused if the agent is influenced by malicious instructions in the processed data.
Audit Metadata