telnyx-account-reports-curl
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documentation includes examples where path parameters (e.g.,
{id},{record_type}), query parameters, and JSON bodies are used within shell commands. If an agent implements these by directly interpolating untrusted user data into the command string, it could lead to API manipulation or command injection. - Ingestion points: Path variables like
{id}and{record_type}in URL paths, as well as query string values and JSON data fields inPOSTrequests. - Boundary markers: The skill does not provide specific instructions or delimiters to isolate user-provided data within these commands.
- Capability inventory: The skill relies on
curlfor network operations and command execution within a shell environment. - Sanitization: No sanitization or validation logic is described for handling dynamic input values.
- [COMMAND_EXECUTION]: The skill consists primarily of
bashscripts andcurlcommands intended to be executed by the agent. This capability allows for direct interaction with external APIs but requires the agent to manage shell execution safety.
Audit Metadata