deploy-webhook
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows security best practices by explicitly instructing the agent never to print API keys, OAuth tokens, webhook secrets, or environment variables in logs or chat responses. It also correctly directs the agent to retrieve credentials from a local configuration file (~/.build-host/credentials.json) rather than requesting them from the user.
- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection because it instructs the agent to read and act upon external application and build logs during debugging steps.
- Ingestion points: Build and runtime logs are retrieved via the
GET /api/projects/:uuid/logsendpoint (SKILL.md). - Boundary markers: No specific delimiters or instructions to ignore instructions within logs are provided.
- Capability inventory: The agent has capabilities to create projects, configure runtime inputs, and trigger deployments via the build.host API (SKILL.md).
- Sanitization: No explicit sanitization or filtering of log content is mentioned before the agent processes the logs to determine the next fix.
Audit Metadata