bro
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of natural language instructions and does not include any executable scripts, binaries, or command-line operations.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies the conversation history as an ingestion point by instructing the agent to restate the most recent message. If the previous message contains malicious instructions, they could be re-processed.
- Ingestion points: Conversation history (specifically the text of the last message).
- Boundary markers: No delimiters or safety instructions are used to distinguish the text being restated from the agent's operational context.
- Capability inventory: No dangerous capabilities such as network access, file system operations, or subprocess execution are present in the skill.
- Sanitization: No explicit sanitization or content filtering is applied to the input text before it is simplified.
Audit Metadata