The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for data retrieval.
Evidence: SKILL.md contains several curl examples for interacting with the Paperclip API to fetch page content and list pages.
[DATA_EXFILTRATION]: The skill performs network requests to external endpoints, handling authentication tokens via environment variables.
Evidence: Requests are directed to https://your-paperclip-host.example.com (or other inferred hosts) using an Authorization: Bearer $TOKEN header.
[PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection due to the ingestion of external data.
Ingestion points: Markdown content retrieved from the /api/plugins/paperclipai.plugin-llm-wiki/data/page-content endpoint.
Boundary markers: No specific delimiters or instructions are provided to the agent to treat fetched data as untrusted or to ignore embedded instructions.
Capability inventory: The agent uses curl to perform network operations and may interact with the paperclipai CLI tool.
Sanitization: There is no evidence of sanitization or validation of the content fetched from the wiki before it is processed by the agent.

paperclip-wiki-fetch