managing-subscriptions
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a feature allowing users to provide instructions for AI-generated summaries via the
summary_prompt_guideparameter. This represents an attack surface for indirect prompt injection. - Ingestion points: The
summary_prompt_guideparameter used insubscriptions-createandsubscriptions-partial-update(SKILL.md). - Boundary markers: Absent; no specific delimiters or instruction-ignoring warnings are defined for the AI summary feature.
- Capability inventory: The skill can create or update subscriptions that deliver data to external targets like email, Slack, and webhooks using tools such as
subscriptions-createandsubscriptions-partial-update. - Sanitization: Absent; no explicit sanitization or validation logic is defined for the user-supplied prompt guide string.
Audit Metadata