The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external, untrusted web content through search queries, which is a potential surface for indirect prompt injection attacks.
Ingestion points: Results returned by the agent's built-in WebSearch tool.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in search results.
Capability inventory: Invokes external data retrieval via the WebSearch tool.
Sanitization: No filtering or sanitization of search result content is specified.
[NO_CODE]: The skill is comprised entirely of Markdown documentation and YAML metadata. No scripts, binaries, or automated shell commands are included in the skill definition.
[SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill uses standard documentation practices for agent capabilities.

web-search