rails-deep-research

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection through its multi-source research methodology.
  • Ingestion points: Untrusted data from third-party websites enters the agent context via the webFetch tool in Phase 3 and the 'Search' phase of the workflow.
  • Boundary markers: Absent. The skill does not instruct the agent to use delimiters or to treat retrieved content as untrusted data rather than instructions.
  • Capability inventory: The skill utilizes webSearch, webFetch, and orchestrates multi-agent tasks using a custom workflow tool.
  • Sanitization: Absent. External findings are synthesized into reports without sanitization or validation of the content source integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 02:20 PM
Security Audit — agent-trust-hub — rails-deep-research