The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, which is a known vector for indirect prompt injection attacks.
Ingestion points: The instructions direct the agent to gather and assess data from "logs, metrics, traces, and system state" (SKILL.md).
Boundary markers: The skill does not define explicit delimiters or instructions to treat data as untrusted or to ignore instructions embedded within the logs or traces.
Capability inventory: The skill lists extensive capabilities, including the use of kubectl, network analysis tools (tcpdump, dig, nslookup), and cloud platform CLIs. An attacker could potentially embed instructions in log messages that the agent might inadvertently follow while troubleshooting.
Sanitization: There are no requirements or methods specified for sanitizing or validating external content before it is processed by the agent.
[NO_CODE]: The skill consists entirely of markdown instructions and metadata, with no executable scripts, configuration files, or automated dependencies provided in the analyzed package.

devops-troubleshooter