effect
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to clone the
effect-smolrepository fromhttps://github.com/Effect-TS/effect-smol. This download targets the official source for the library to provide the agent with up-to-date documentation and code samples. - [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by instructing the agent to read and follow patterns from external repository content and local files.
- Ingestion points: Files and documentation within the
.opencode/references/effect-smoldirectory and the local project codebase. - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: The skill is designed for code generation and style enforcement; it does not request high-risk capabilities like arbitrary command execution or network exfiltration based on the ingested content.
- Sanitization: No specific validation or sanitization of the external reference content is performed beyond the agent's standard processing.
Audit Metadata