desk-research

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data for analysis purposes.
  • Ingestion points: Processes logs, CSV exports, and usage analytics as described in SKILL.md.
  • Capability inventory: Encourages the creation of notebooks and scripts for data processing.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for data content.
  • Sanitization: The workflow does not explicitly detail sanitization procedures for ingested data.
  • [EXTERNAL_DOWNLOADS]: The skill references repositories and datasets from public sector organizations.
  • Evidence: Mentions the GSA-TTS/10x-web-performance-optimization-research and uswds/uswds-elements projects as reference examples for research workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 03:56 PM
Security Audit — agent-trust-hub — desk-research