build-context
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external content such as codebases, project notes, and conversation history to extract terminology. This creates a surface where instructions embedded in those sources could potentially influence the agent's behavior during the glossary generation process.
- Ingestion points: Reads from conversation history, project files (README.md, AGENTS.md, project notes), and codebase identifiers (function names, database columns) in SKILL.md.
- Boundary markers: The instructions do not specify the use of clear delimiters or warnings to ignore embedded instructions when processing these sources.
- Capability inventory: The skill has the capability to write files (CONTEXT.md) to the local filesystem and interact with the user via terminal prompts.
- Sanitization: No explicit sanitization or filtering of the ingested content is described beyond a manual user confirmation step for suggested definitions.
Audit Metadata