The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes API access logs and analytics data, which constitute a surface for indirect prompt injection as they ingest strings (such as User-Agents or URIs) provided by external callers.
Ingestion points: api_log-list and api_analytics-list tools used in the standard workflow defined in SKILL.md.
Boundary markers: Instructions do not explicitly define delimiters or specific warnings to ignore instructions embedded within the log data.
Capability inventory: The skill possesses configuration update capabilities via api-upsert_api and api-upsert_uri, although the documentation notes restrictions and requires user approval for such actions.
Sanitization: There is no evidence of specific escaping or filtering of log data before it is processed by the agent to generate reports.
[SAFE]: All external resource references are directed toward official documentation on the kuroco.app domain.
[SAFE]: The skill's functionality is consistent with its stated purpose as a vendor-provided diagnostic tool, utilizing official administrative interfaces for performance monitoring and usage analysis.

kuroco-api-performance-review