paper-assembly
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- PROMPT_INJECTION (LOW): Detected indirect prompt injection vulnerability surface. * Ingestion points: Processes files within the project directory (e.g., paper/, knowledge_base.json, results.json, main.tex). * Boundary markers: Absent; the skill does not use delimiters or instructions to ignore embedded commands in the processed artifacts. * Capability inventory: Executes local scripts via python, writes to the filesystem, and orchestrates a chain of other functional skills. * Sanitization: Absent; no evidence of validation or filtering for data ingested from the paper project artifacts.
- COMMAND_EXECUTION (SAFE): The skill executes a local utility script (assembly_checker.py) to manage the pipeline state. This is consistent with its primary purpose as an orchestrator.
Audit Metadata