The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes link-state topology data, including node metadata and event logs, from an external API. This data represents a surface for indirect prompt injection if the ingested content contains instructions designed to influence the agent.
Ingestion points: External data is processed via tools like get_graph_by_time, get_nodes, and get_events_timeline in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to treat external network data as untrusted content.
Capability inventory: The skill is restricted to analytical functions; it lacks capabilities for arbitrary shell execution, file system modification, or persistence mechanisms.
Sanitization: No specific filtering or sanitization of the API-returned topology data is mentioned.
[EXTERNAL_DOWNLOADS]: The skill references and communicates with https://topolograph.com/mcp, which is the official endpoint for the topology analysis service described in the skill.
[SAFE]: The skill documentation correctly specifies that the TOPOLOGRAPH_API_TOKEN should be provided via environment variables, adhering to standard security practices for credential handling.

topolograph-igp-analysis