business-domain-context
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local shell commands using
bun run context:mapto retrieve domain context andgit logto verify if project artifacts have been updated. These operations are scoped to the project environment and are necessary for the skill's primary function of context synchronization. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it ingests untrusted data from external sources to update its domain map.
- Ingestion points: Processes data from
references/business-domain-map.html, project backlog stories in.context/PBI/(synced from Jira), UI labels, and source code repositories ({{FRONTEND_REPO}},{{BACKEND_REPO}}). - Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the ingested data are defined in the instructions.
- Capability inventory: The agent possesses shell execution capabilities (
bun,git) and write access to thereferences/directory. - Sanitization: There are no explicit sanitization or filtering steps mentioned for the external content before it is processed or used to refine the glossary.
Audit Metadata