research-strategy-brief

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data sources such as government policy documents and funding agency guidelines, which represents an indirect prompt injection surface.
  • Ingestion points: WebSearch and WebFetch results from government and funding agency websites (SKILL.md).
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore embedded instructions in external data.
  • Capability inventory: The skill utilizes the Bash tool for data formatting and aggregation (SKILL.md).
  • Sanitization: No explicit sanitization or validation of external content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 03:36 AM
Security Audit — agent-trust-hub — research-strategy-brief