research-to-json

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes markdown files from the research/ directory which could contain untrusted data.
  • Ingestion points: Reads all markdown files located in the research/ directory.
  • Boundary markers: Absent. The skill does not explicitly instruct the agent to ignore instructions that might be embedded within the research files.
  • Capability inventory: Limited to reading files from research/ and writing structured JSON files to data/.
  • Sanitization: The skill employs a rigid "Output contract" (JSON schema) and explicit "Mapping rules" that enforce data normalization and faithfulness to the source text, which helps mitigate risks associated with untrusted input data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:15 PM
Security Audit — agent-trust-hub — research-to-json