tldr
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions focus on transforming technical content into a concise summary format. It utilizes standard code reading tools to access project files, which is consistent with its stated purpose of explaining code and architecture.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from local files to generate summaries. However, this is a core requirement for its primary purpose, and the agent's capabilities are restricted to providing explanations without performing dangerous operations based on the ingested content.
- Ingestion points: The skill identifies and reads target files and symbols via file system tools in Step 1.
- Boundary markers: Absent; there are no specific instructions to disregard instructions within the code being summarized.
- Capability inventory: File system read access via agent tools for summarization.
- Sanitization: None; the content is processed directly for technical explanation.
Audit Metadata