bro
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user-selected text or previous messages, creating a surface for indirect prompt injection.
- Ingestion points: User-selected text or the last message in the context (SKILL.md).
- Boundary markers: None provided to separate instructions from user data.
- Capability inventory: None. The skill explicitly sets
disable-model-invocation: true, preventing the agent from calling tools, accessing the network, or writing to the file system. - Sanitization: No sanitization or filtering of input text is performed.
- [SAFE]: No malicious patterns, obfuscation, or persistence mechanisms were detected. The natural language instructions are focused solely on stylistic text simplification.
- [NO_CODE]: The skill consists entirely of natural language instructions and configuration metadata. There are no scripts, binaries, or package dependencies included.
Audit Metadata