skills/howells/skills/mastraudit/Gen Agent Trust Hub

mastraudit

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to perform technical audits on external Mastra codebases, which involves ingesting untrusted source code and documentation into the agent's context. This creates a potential surface where malicious instructions embedded in the audited files could attempt to influence the agent's behavior.\n
  • Ingestion points: The agent is instructed to read local node_modules packages, documentation files, and the codebase being audited including agents, tools, and workflows.\n
  • Boundary markers: The instructions provide a structured Output contract and a step-by-step checklist to maintain auditor focus, but they do not define explicit delimiters or unique markers to isolate the ingested codebase content from the agent's primary instructions.\n
  • Capability inventory: The auditing process involves reading and analyzing file contents, identifying specific code patterns, and recording the output of vendor-supplied scanner functions from the @howells/mastra package.\n
  • Sanitization: There are no explicit instructions to sanitize, escape, or filter the contents of the audited codebase before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 07:03 AM
Security Audit — agent-trust-hub — mastraudit