runpod-pod-deploy
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data that may contain adversarial instructions.
- Ingestion points: External content is ingested via
stream-pod-logs(boot logs) and from the descriptions of templates and Hub-repositories during the discovery phase. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present to protect the agent context from ingested data.
- Capability inventory: The skill possesses significant capabilities including pod creation (
create-pod), pod deletion (delete-pod), volume management, and modification of account SSH keys (update-ssh-keys). - Sanitization: The instructions do not mandate sanitization, filtering, or validation of the content read from logs or external repositories before it is presented to the agent context.
Audit Metadata