workflow-automator

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a potential surface for indirect prompt injection because it processes untrusted user-provided descriptions of manual workflows while having access to sensitive tools.
  • Ingestion points: Untrusted data enters the agent context through the manual workflow descriptions provided by the user during the intake phase (referenced in references/intake.md).
  • Boundary markers: The skill instructions lack explicit boundary markers or instructions for the agent to ignore any embedded directives within the user's workflow description.
  • Capability inventory: The skill has access to several powerful tools including Bash, Write, WebFetch, Glob, and Grep as defined in the SKILL.md frontmatter.
  • Sanitization: There are no documented procedures for sanitizing, escaping, or validating the external content before it is processed or interpolated into the analysis phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:02 PM
Security Audit — agent-trust-hub — workflow-automator