vault-mounts
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes data (secret engine configurations and names) from an external HashiCorp Vault server. An attacker with the ability to modify Vault configurations could potentially embed instructions aimed at the agent.
- Ingestion points: The list_mounts, get_mount, and list_auth_methods tools ingest external data into the agent context from the Vault API.
- Boundary markers: The skill does not define specific delimiters or warnings to ignore embedded instructions in the ingested data.
- Capability inventory: The skill has administrative and destructive capabilities, including create_mount, delete_mount, and tune_mount.
- Sanitization: No explicit validation or filtering of data returned from the Vault API is documented within the skill instructions.
- [CREDENTIALS_UNSAFE]: The skill requires a VAULT_TOKEN for authentication. The instructions correctly advise users to provide this through environment variables, which is a standard and secure practice for managing secrets in this context. Users should ensure the token is scoped to the minimum permissions required.
Audit Metadata