ncode-prompt-guide
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for the agent to ingest and restructure vague user prompts into more specific ones. This processing of untrusted user data establishes a potential surface for indirect prompt injection.
- Ingestion points: User input strings provided to the agent for refinement as outlined in SKILL.md.
- Boundary markers: The skill does not implement delimiters or specific instructions to help the agent distinguish between user data and instructions.
- Capability inventory: The agent operates within its standard execution environment with capabilities to write files and execute shell commands.
- Sanitization: There are no specific mechanisms described for sanitizing or validating user input before it is processed by the agent.
Audit Metadata