specsfy-specialist-deploy

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local automation scripts (scaffold.mjs, check-hosts.py) and Ansible CLI tools to manage project infrastructure and verify connectivity. It also utilizes a dedicated shell script (create-vault.sh) that uses hidden terminal input to securely handle sensitive secrets without exposing them to the AI's internal context.
  • [PRIVILEGE_ESCALATION]: The generated Ansible playbooks utilize become: true to perform root-level system configurations and assign the service user to the docker group, providing the elevated permissions required for remote infrastructure management.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes existing project files like Dockerfile, compose.yaml, and SEMVER to reconcile configurations, which creates a potential surface for untrusted content within the user's project to influence the agent's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 10:43 PM
Security Audit — agent-trust-hub — specsfy-specialist-deploy