lit-synthesizer

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests external research papers for synthesis, which presents an indirect prompt injection surface. This is a characteristic of the primary synthesis task and is managed through sequential processing and downstream fact-checking.
  • Ingestion points: Input files (reviews, sections) are read from directories specified in the task configuration (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified.
  • Capability inventory: The skill is limited to reading and writing text files within designated scratchpad areas.
  • Sanitization: No sanitization or content validation is performed.
  • [SAFE]: The skill implements archival compliance checks using established internal file paths.
  • [SAFE]: No network access, package installation, or shell command execution was found in the skill definitions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 06:21 PM