bmad-spec

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill acts as a text processor using a predefined markdown template. \n- [NO_CODE]: The skill consists purely of Markdown instructions and templates. No Python, JavaScript, or shell scripts are present, which prevents any code-based attacks. \n- [PROMPT_INJECTION]: The skill's ingestion of untrusted meeting transcripts and notes constitutes a surface for indirect prompt injection. However, this is assessed as safe given the tool's limited capability to only modify local markdown files without network or execution privileges. \n
  • Ingestion points: User-provided text, notes, and transcripts ingested via the Read tool (SKILL.md). \n
  • Boundary markers: None; the skill does not explicitly delimit untrusted input from its core instructions. \n
  • Capability inventory: Access is restricted to Read, Write, Edit, Glob, Grep, and TodoWrite for local file management. \n
  • Sanitization: No specific sanitization logic is applied to the ingested text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 12:30 PM
Security Audit — agent-trust-hub — bmad-spec