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, andGrepas defined in theSKILL.mdfrontmatter. - 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