code-simplify
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze recently modified code, which serves as an untrusted data source that could contain malicious instructions.
- Ingestion points: The agent is instructed in
references/simplifier.mdto analyze 'recently modified code'. - Boundary markers: The system prompt lacks explicit delimiters or clear instructions to disregard any Natural Language instructions that might be embedded within comments or string literals in the source code being analyzed.
- Capability inventory: The skill is intended to be used by a
general-purposetask agent, which usually possesses the ability to read and write to the file system. - Sanitization: No mechanisms are provided to sanitize or validate the content of the code before processing it, leaving the agent susceptible to instructions hidden within the data.
Audit Metadata