byted-ind-h-edu-prj-apply-material

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill operates as intended for generating academic project proposal documents. All scripts and templates are clear, readable, and focused on the stated purpose. No malicious code, data exfiltration, or persistence mechanisms were found.\n- [COMMAND_EXECUTION]: The skill includes a shell script setup.sh for environment preparation and a Python script generate_apply_material.py for document creation. These scripts are intended for local environment setup and execution, which is consistent with the skill's utility functions.\n- [PROMPT_INJECTION]: The skill processes user-defined inputs like research topics and applicant names by interpolating them into document templates. While this creates a potential surface for indirect prompt injection if the generated output is later used as an LLM prompt, it is a low-risk design choice for a document generation tool.\n
  • Ingestion points: User-provided CLI arguments (--topic, --applicant, --organization) in scripts/generate_apply_material.py.\n
  • Boundary markers: Absent in generated templates.\n
  • Capability inventory: Local file system write access in scripts/generate_apply_material.py.\n
  • Sanitization: Absent; the script performs direct string interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 06:17 AM
Security Audit — agent-trust-hub — byted-ind-h-edu-prj-apply-material