to-tickets
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill focuses on developer productivity by organizing work into vertical slices. It uses standard platform tools like
AskUserQuestionandask_userfor interactive confirmation, ensuring user oversight during the breakdown process. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources such as GitHub issue bodies and comments. While this is necessary for its function, it creates a vector where embedded instructions in those sources could influence agent behavior.
- Ingestion points: Reads full bodies and comments from referenced issues, plans, or URLs provided in the conversation context (SKILL.md).
- Boundary markers: There are no instructions to wrap or delimit this external content to prevent it from being interpreted as instructions.
- Capability inventory: The skill uses GitHub issue creation and a general-purpose
workskill to perform implementation tasks (SKILL.md). - Sanitization: No procedures are specified for sanitizing or escaping the retrieved external content before processing.
Audit Metadata