salla-app-expert
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill includes instructions that attempt to override the agent's standard behavior or general knowledge. It uses phrases like 'its instructions MUST be followed' and 'a stated requirement overrides familiar generic patterns' to anchor the agent's operational logic specifically to this skill's rules.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a significant attack surface for indirect injection by routing events and intents to specialized handlers.
- Ingestion points: The skill routes store events such as webhooks, App Functions triggers, and storefront snippets (SKILL.md).
- Boundary markers: None are defined in this router skill to separate external event data from agent instructions.
- Capability inventory: The skill uses a wide range of MCP tools including
salla_apps,salla_events,salla_snippets,salla_embedded_pages,salla_onboarding_steps,salla_settings,salla_shipping, andsalla_functions(SKILL.md). - Sanitization: No sanitization or validation logic is present in this routing layer to handle external content before it is passed to sub-skills.
Audit Metadata