code-walkthrough
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (source code, directories, and PRs) and uses the Artifact tool to generate output, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill reads target files, directories, or pull requests as specified in the 'Explore first' section.
- Boundary markers: The instructions do not define explicit boundary markers or provide warnings to ignore embedded instructions within the analyzed code.
- Capability inventory: The skill utilizes the Artifact tool to write and publish HTML artifacts based on the processed code.
- Sanitization: There is no requirement in the instructions to sanitize or escape code snippets or the generated analysis to prevent potential prompt overrides hidden in code comments or strings.
Audit Metadata