vexdock-api
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Vexdock API (container logs, command output, and database records). This data could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: API responses in
SKILL.md(via endpoints such as/api/services/$SERVICE/logs,/api/services/$SERVICE/exec, and/api/services/$SERVICE/studio/rows). - Boundary markers: Absent.
- Capability inventory: The skill can execute commands in containers (
/api/services/$SERVICE/exec), perform database queries (/api/services/$SERVICE/studio/query), and manage system deployments. - Sanitization: Not explicitly mentioned in the instructions for processing external content.
Audit Metadata