makepad-event-action
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions mandate that the agent read and incorporate content from local reference files (
./references/event-system.mdand./references/action-system.md) before responding. This creates an indirect prompt injection surface where instructions or malicious patterns embedded in those data files could influence the agent's behavior. - Ingestion points: The agent is instructed to load and read content from external paths:
./references/event-system.mdand./references/action-system.md(specified inSKILL.md). - Boundary markers: There are no boundary markers or instructions to treat the content of the reference files as untrusted data or to ignore any embedded instructions therein.
- Capability inventory: The skill itself is restricted to documentation and code snippets; it does not request tool access to perform network operations, file writes, or command execution.
- Sanitization: No sanitization or validation logic is defined for the content ingested from the external reference files.
Audit Metadata