The Agent Skills Directory

[Dynamic Execution] (LOW): The skill utilizes bash -c to execute shell commands as a workaround for environment variable handling in specific agent environments. While functional, wrapping commands in strings for execution is a form of dynamic command construction.
[Data Exposure & Exfiltration] (LOW): The skill performs network operations to api.axiom.co and aws.edge.axiom.co. These domains are required for the skill's primary function but are not included in the predefined whitelist of trusted domains.
[Indirect Prompt Injection] (LOW): The skill creates a surface for indirect prompt injection by processing external data (logs and events) that could contain malicious instructions.
Ingestion points: User-provided log data and event payloads written to /tmp/axiom_request.json and /tmp/axiom_ndjson.ndjson.
Boundary markers: Absent; data is passed directly to the API via curl.
Capability inventory: File system write access and network communication via curl executed through bash.
Sanitization: None observed; the skill assumes the integrity of the data being ingested and sent to the platform.

axiom