think-role-storming
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists exclusively of Markdown instructions and YAML metadata without any executable scripts or binaries.
- [PROMPT_INJECTION]: While the skill uses persona adoption (role-play), the instructions are constrained to creative ideation and include explicit checks to prevent the agent from bypassing its safety guidelines or misusing the technique for evaluation or dissent.
- [DATA_EXFILTRATION]: No network operations (such as curl or wget) or sensitive file system access patterns were detected in the instructions or metadata.
- [REMOTE_CODE_EXECUTION]: There are no external package dependencies or remote script fetching patterns present in the skill files.
- [OBFUSCATION]: All content is provided in cleartext with no evidence of Base64 encoding, zero-width characters, or homoglyph attacks.
- [METADATA_POISONING]: Metadata fields accurately describe the skill's purpose and lineage without containing deceptive instructions.
Audit Metadata