graphify-cli
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes structured data from code graph files that are derived from repository content, creating a surface for indirect instructions.
- Ingestion points: The agent is instructed to read and parse data from
.ai/graphify-out/graph.jsonand~/.graphify/global-graph.json(SKILL.md). - Boundary markers: The skill lacks explicit instructions for the agent to treat data retrieved from graph nodes as untrusted or to use delimiters when processing node labels or metadata.
- Capability inventory: The skill utilizes a suite of MCP tools (e.g.,
query_graph,get_node) and falls back to standard filesystem tools includingread,grep, andglobfor validation. - Sanitization: There are no documented procedures for sanitizing or validating the contents of the graph files before they are interpreted by the agent.
Audit Metadata