The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The install_command in metadata.json downloads the skill content from a non-trusted GitHub repository (github.com/sickn33/antigravity-awesome-skills). While GitHub is a well-known service, the specific account and repository are not recognized as trusted or official vendor resources.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) due to its primary function of processing untrusted data.
Ingestion points: The skill is designed to analyze logs, distributed traces, APM data, and system metrics from various external platforms (ELK, Datadog, etc.).
Boundary markers: There are no boundary markers or instructions telling the agent to ignore potentially malicious instructions embedded within the logs or observability data being analyzed.
Capability inventory: The instructions grant the agent capabilities to execute diagnostic commands and interact with infrastructure tools such as kubectl, tcpdump, and dig.
Sanitization: The skill lacks any instructions for sanitizing, validating, or escaping external content before the agent acts upon it.

devops-troubleshooter