workflow-guide
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill consists entirely of Markdown documentation and metadata. No executable scripts, obfuscated code, or malicious command patterns were detected.
- [INDIRECT_PROMPT_INJECTION] (LOW): The workflow described involves the agent reading a file named
Plans.mdto determine tasks. This presents a theoretical surface for indirect prompt injection where instructions could be embedded in the task list. - Ingestion points:
Plans.md,AGENTS.md,CLAUDE.md. - Boundary markers: Absent; the workflow uses standard Markdown markers (e.g.,
cc:TODO). - Capability inventory: The skill itself only requests
Readpermissions, limiting the impact of any potential injection. - Sanitization: Not applicable as the skill is informational.
Audit Metadata