The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, persistence mechanisms, or unauthorized privilege escalation attempts were detected within the skill instructions or metadata.
[EXTERNAL_DOWNLOADS]: The skill communicates with Datadog's official API endpoints at datadoghq.com, which is a recognized and well-known service provider.
[PROMPT_INJECTION]: The skill processes external trace data from Datadog logs, creating an ingestion surface for potential indirect instructions. However, the risk is mitigated as the skill lacks high-privilege capabilities such as file system writes, network exfiltration to unknown hosts, or shell command execution.
Ingestion points: External data enters the agent context via search_traces and get_trace_details tools defined in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided.
Capability inventory: Capabilities are restricted to read-only informational API queries; no subprocess or dynamic execution tools are available.
Sanitization: No specific sanitization or filtering of external trace content is implemented.

datadog-apm