skills/reforma-dev/agentflow/research/Gen Agent Trust Hub

research

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to search the web and read external documentation. This creates an attack surface where malicious instructions embedded in third-party websites could influence the agent's behavior during the research process.
  • Ingestion points: External websites, primary documentation, and codebase files (SKILL.md).
  • Boundary markers: The skill suggests a structured Markdown format for research notes, which provides some implicit separation between retrieved content and the final report.
  • Capability inventory: The skill has the capability to write research maps and topic pages to the local filesystem under the .agentflow/ directory.
  • Sanitization: There are no explicit instructions for the agent to sanitize or escape content retrieved from the web before documenting it.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 04:28 PM
Security Audit — agent-trust-hub — research