ontoly-software-graph
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run local shell commands, such as
ontoly build .andontoly mcp, which are necessary for analyzing the codebase as part of its primary functionality. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external source code, creating a surface for indirect prompt injection if the repository contains malicious instructions.
- Ingestion points: TypeScript source files are processed via the
ontolyCLI tool during graph generation (SKILL.md). - Boundary markers: There are no instructions to use specific delimiters or ignore instructions found within the repository files.
- Capability inventory: The agent can execute
ontolycommands for building graphs and starting an MCP server, as well asfindfor file searching (SKILL.md). - Sanitization: The skill does not provide methods for sanitizing or filtering data extracted from the repository before it is presented to the agent.
Audit Metadata