The Agent Skills Directory

[DATA_EXFILTRATION]: The skill performs network requests to https://plugin.anspire.cn/api/ntsearch/search using the ANSPIRE_API_KEY provided in the environment. While this is the core functionality of the skill, it involves sending user-generated queries to an external service.
[COMMAND_EXECUTION]: The skill uses the curl binary to perform its network operations, as defined in the SKILL.md instructions and documented in the metadata requirements.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the web, creating a potential injection surface.
Ingestion points: The agent is instructed to read JSON responses from the Anspire Search API and extract title, url, and snippet fields to summarize for the user.
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be embedded within the search results (e.g., within a page snippet).
Capability inventory: The skill has network access capabilities via curl to fetch external content.
Sanitization: The instructions do not mention any validation, filtering, or escaping of the content retrieved from the search API before it is processed by the agent.

anspire-web-search