effect-collections-datastructs
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): The skill contains instructional content without any attempts to override system prompts, bypass safety filters, or use role-play for jailbreaking.
- Data Exposure & Exfiltration (SAFE): The skill references local documentation paths (docs/effect-source/) and does not attempt to access sensitive system files or credentials.
- Remote Code Execution (SAFE): No remote scripts are downloaded, and no external code is executed at runtime. All commands are standard local search operations (grep).
- Indirect Prompt Injection (LOW): The skill instructs the agent to ingest local source code files as a primary reference. While this exposes a surface for indirect prompt injection if the source files themselves were compromised, the pattern is part of the skill's intended documentation-search purpose and is considered low risk.
Audit Metadata