The Agent Skills Directory

[SAFE]: No malicious patterns were identified in the skill instructions or scripts. The skill is designed for network environment diagnostics and follows best practices for read-only evidence collection.
[COMMAND_EXECUTION]: The skill suggests executing standard network troubleshooting commands such as show bgp summary, ping, and traceroute. These are typical for the stated purpose of BGP diagnostics and do not involve unauthorized privilege escalation or persistence.
[PROMPT_INJECTION]: The skill includes a Python function parse_bgp_summary that processes external data from CLI output, representing a surface for indirect prompt injection.
Ingestion points: The raw string input in parse_bgp_summary function (SKILL.md).
Boundary markers: None present.
Capability inventory: No subprocess calls, file writes, or network operations are present in the skill scripts.
Sanitization: The code uses a strict regular expression BGP_SUMMARY_RE to extract only specific structured data fields, which effectively mitigates the risk of the agent following instructions embedded in the input text.

network-bgp-diagnostics