Strands Agents Tools
Monthly
Prompt injection in Amazon Strands Agents Tools before 0.8.0 enables remote actors to execute arbitrary OS commands on the agent's host by crafting input that sets the shell tool's `non_interactive` parameter to `true`, silencing the human consent gate designed to require approval before running shell commands. The CVSS 4.0 vector (AV:N/PR:N) confirms no attacker authentication is required, though the agent must actively process the malicious prompt (UI:A) and the shell tool must be in use (AT:P). No public exploit code or CISA KEV listing has been identified at time of analysis.
Credential exfiltration in AWS Strands Agents Tools before 0.8.2 exposes HTTP_REQUEST_TOKEN_CONFIG bearer tokens to attacker-controlled proxy infrastructure by exploiting the LLM's ability to set proxy parameters within the http_request tool's input schema. The root cause (CWE-863: Incorrect Authorization) is that proxy configuration was included as an LLM-controllable field, enabling prompt injection attacks to redirect credentialed HTTP requests through adversary infrastructure. No public exploit code or CISA KEV listing has been identified at time of analysis; however, any deployment combining token-authenticated HTTP requests with externally influenced agent inputs is at material risk.
Server-side request forgery in the strands-agents-tools elasticsearch_memory tool enables prompt-injection attacks that exfiltrate the operator's Elasticsearch API key to attacker-controlled infrastructure. Applications using strands-agents-tools prior to 0.7.0 that rely on the ELASTICSEARCH_API_KEY environment-variable fallback - rather than explicitly passing api_key - are exposed to credential theft when an attacker can influence LLM input. No public exploit code or CISA KEV listing has been identified at time of analysis, but the prompt-injection-to-SSRF primitive is well understood in the AI agent security community and the credential-theft impact warrants prompt remediation.
Prompt injection in Amazon Strands Agents Tools before 0.8.0 enables remote actors to execute arbitrary OS commands on the agent's host by crafting input that sets the shell tool's `non_interactive` parameter to `true`, silencing the human consent gate designed to require approval before running shell commands. The CVSS 4.0 vector (AV:N/PR:N) confirms no attacker authentication is required, though the agent must actively process the malicious prompt (UI:A) and the shell tool must be in use (AT:P). No public exploit code or CISA KEV listing has been identified at time of analysis.
Credential exfiltration in AWS Strands Agents Tools before 0.8.2 exposes HTTP_REQUEST_TOKEN_CONFIG bearer tokens to attacker-controlled proxy infrastructure by exploiting the LLM's ability to set proxy parameters within the http_request tool's input schema. The root cause (CWE-863: Incorrect Authorization) is that proxy configuration was included as an LLM-controllable field, enabling prompt injection attacks to redirect credentialed HTTP requests through adversary infrastructure. No public exploit code or CISA KEV listing has been identified at time of analysis; however, any deployment combining token-authenticated HTTP requests with externally influenced agent inputs is at material risk.
Server-side request forgery in the strands-agents-tools elasticsearch_memory tool enables prompt-injection attacks that exfiltrate the operator's Elasticsearch API key to attacker-controlled infrastructure. Applications using strands-agents-tools prior to 0.7.0 that rely on the ELASTICSEARCH_API_KEY environment-variable fallback - rather than explicitly passing api_key - are exposed to credential theft when an attacker can influence LLM input. No public exploit code or CISA KEV listing has been identified at time of analysis, but the prompt-injection-to-SSRF primitive is well understood in the AI agent security community and the credential-theft impact warrants prompt remediation.