the-oracle
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill explicitly includes a "Skepticism Protocol" and "Anti-Priming Protocol." These instructions are designed to defend the agent against biased or malicious instructions from the invoker, requiring the sub-agent to perform independent verification of all claims.
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard repository exploration tools such as
git log,grep, andglob. These operations are limited to the local environment and are appropriate for the skill's stated purpose of codebase research. - [EXTERNAL_DOWNLOADS]: The agent is authorized to use a
WebSearchtool for retrieving external documentation. This is a standard feature for research agents and does not involve the execution of untrusted remote code. - [DATA_EXPOSURE]: The skill accesses project-specific files such as
.oracle/research logs, git history, and.plans/. No hardcoded credentials or sensitive system-level paths were detected.
Audit Metadata