workflow-sprint-retro
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user input directly as context for its internal workflow logic.
- Ingestion points: User input is passed as context to the /workflow-start command in SKILL.md.
- Boundary markers: The skill does not use delimiters or isolation instructions to distinguish between its own logic and the data provided in the user prompt.
- Capability inventory: The skill triggers several workflow management commands including /workflow-start, /status, /retro, and /workflow-end.
- Sanitization: There is no evidence of sanitization, escaping, or validation of the user's input before it is utilized by the agent commands.
Audit Metadata