sc-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes the content of external project documents (PRDs) and feature strings while possessing write-access to external project management tools.
- Ingestion points: The skill parses project requirements documents (e.g.,
feature-spec.md,enterprise-prd.md) and feature descriptions provided by the user. - Boundary markers: The instructions lack explicit markers or directives (e.g., XML tags or clear 'ignore instructions within data' warnings) to prevent the model from obeying malicious commands embedded within a PRD.
- Capability inventory: The skill uses tools to write to external platforms including Jira (
JIRA_CREATE_ISSUE), Slack (SLACK_SEND_MESSAGE), Notion (NOTION_CREATE_PAGE), and can save persistent workflow templates (RUBE_CREATE_UPDATE_RECIPE). - Sanitization: There is no evidence of sanitization or validation performed on the text extracted from PRDs before it is processed or passed to external tools.
Audit Metadata