The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to retrieve and analyze external log data through the list_log_entries tool, which constitutes a surface for indirect prompt injection. Log entries (such as application errors, DNS queries, or VPC flow metadata) are untrusted sources that could contain malicious instructions designed to influence the agent's behavior during analysis.
Ingestion points: SKILL.md defines workflows using the list_log_entries tool to ingest external log data into the agent context.
Boundary markers: The skill does not provide specific delimiters or instructions for the agent to treat log content as untrusted data.
Capability inventory: The skill provides read-only capabilities including list_log_entries, list_log_names, get_bucket, list_buckets, get_view, and list_views.
Sanitization: No sanitization or filtering of log entry content is specified in the skill instructions.
[EXTERNAL_DOWNLOADS]: The skill connects to a remote MCP endpoint at logging.googleapis.com. This is a well-known service provided by Google and is used for legitimate cloud logging operations.

gcp-cloud-logging