workflow-e2e-from-changes
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests user input as context for the workflow-start command, establishing an indirect prompt injection surface where external input could manipulate the agent's workflow execution logic.
- Ingestion points: User input passed to the /workflow-start command in SKILL.md.
- Boundary markers: Absent. No delimiters or instructions are provided to the agent to distinguish user content from its own system instructions.
- Capability inventory: The workflow involves sequential execution of /scout, /e2e-test, /test, and /watzup commands which likely interact with the file system and test environment.
- Sanitization: Absent. No input validation or filtering is specified for the user-provided context.
Audit Metadata