syslog-receiver
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes syslog messages from external, untrusted sources (network devices) via the
syslog_queryandsyslog_get_messagetools. - Ingestion points: External syslog data enters the agent context when using tools like
syslog_queryorsyslog_get_messageto view collected logs. - Boundary markers: The skill documentation does not define specific delimiters or instructions to prevent the agent from following commands embedded within the syslog messages.
- Capability inventory: The skill provides capabilities to query, view, and analyze logs, which are then used by the agent to report on network status.
- Sanitization: There is no mention of sanitizing or escaping the log content before it is processed by the AI agent.
Audit Metadata