The Agent Skills Directory

[PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection by instructing the agent to process untrusted data sources (logs and traces) while enabling powerful capabilities.
Ingestion points: The skill reads and parses log data (Loki), trace data (Tempo), and dashboard configurations (SKILL.md).
Boundary markers: The templates provided do not include specific delimiters or warnings to ignore instructions embedded within the processed data.
Capability inventory: The skill configuration allows access to Bash, Write, Edit, and Read tools.
Sanitization: There is no evidence of sanitization or escaping of external content before it is interpolated into queries or displayed in the agent's context.
[SAFE]: No malicious patterns, obfuscation, or unauthorized network operations were detected. The skill uses standard placeholders (e.g., YOUR_WEBHOOK_URL) for configuration examples, which is a secure practice.
[EXTERNAL_DOWNLOADS]: The skill references the official grafana-operator repository on GitHub, which is a well-known and trusted source.

loom-grafana