deployment

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill provides instructions to execute local scripts (scripts/test-coolify-build.sh) and build tools (pnpm, npm) using the Bash tool. These commands are integral to the deployment validation process but provide an execution surface for the agent.
  • [EXTERNAL_DOWNLOADS] (LOW): The skill references the use of pnpm install and npm run build, which involve downloading third-party dependencies from external registries. These are standard development operations.
  • [DATA_EXFILTRATION] (SAFE): The skill contains hardcoded references to a specific deployment server at 95.217.155.28:8000. This is used for webhook configuration and monitoring and does not appear to be an exfiltration attempt.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data from repository files to perform automated validation steps.
  • Ingestion points: Deployment configuration files including nixpacks.toml, package.json, and Dockerfile are read to determine the build plan.
  • Boundary markers: Absent; there are no instructions to ignore instructions embedded within the files being processed.
  • Capability inventory: The skill has access to Bash, Write, Edit, and Read tools, which are powerful enough to modify the system or exfiltrate data if the agent is misled.
  • Sanitization: Absent; the skill does not specify any validation or sanitization for the content of the configuration files before they influence the agent's actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:39 PM