bmad-research

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local bash script (scripts/research-sources.sh) to display a research strategy guide. The script is internally managed and contains only text output logic.
  • [EXTERNAL_DOWNLOADS]: The skill uses WebSearch and WebFetch to gather data from various public web sources such as industry reports, competitor sites, and official documentation to populate its research reports.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the live web (e.g., product reviews, social media sentiment, and third-party documentation). This is an inherent risk of its primary research function.
  • Ingestion points: External data retrieved via WebSearch and WebFetch as described in SKILL.md.
  • Boundary markers: The skill uses a structured markdown template (templates/research-report.template.md) to format findings, providing some structural isolation for external content.
  • Capability inventory: The skill has capabilities for file system access (Read, Write, Edit, Glob), command execution (Bash), and network operations (WebSearch, WebFetch) as defined in SKILL.md.
  • Sanitization: No explicit sanitization or filtering of external content is mentioned before interpolation into the report template.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 12:30 PM
Security Audit — agent-trust-hub — bmad-research