explore-codebase
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted codebase data through various graph exploration tools.
- Ingestion points: Codebase structure and content are accessed via tools like
semantic_search_nodes_toolandget_flow_tooldescribed inSKILL.md. - Boundary markers: The instructions do not define delimiters or specific warnings to the agent to ignore instructions embedded within the processed code.
- Capability inventory: The skill leverages tools for architecture overview, semantic search, and execution path analysis.
- Sanitization: There is no evidence of sanitization or filtering of the ingested codebase content within the skill's instructions.
Audit Metadata