crest
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill defines a specific persona (Crest) for product strategy but does not contain any instructions to bypass safety guidelines, override system prompts, or ignore previous instructions.
- [DATA_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or unauthorized data transmission patterns were found. The tools listed in the configuration are standard for the skill's purpose.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts or unverified third-party packages.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided input through the
{{args}}placeholder and passes it to sub-skills. This represents a standard orchestration pattern; while it defines a processing surface for external data, no malicious exploitation logic or unsafe interpolation patterns were identified.
Audit Metadata