The Agent Skills Directory

[DATA_EXPOSURE]: The skill facilitates access to Feishu document content. This behavior is the primary intended function and is performed using official API endpoints (open.feishu.cn) belonging to the vendor (ByteDance). Access is governed by the user's OAuth access token.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it retrieves and processes arbitrary text from external Feishu documents.
Ingestion points: Document content is fetched via the fetch_raw_content method in scripts/feishu_search.py.
Boundary markers: No specific delimiters or boundary markers are instructed for use in the agent instructions within SKILL.md.
Capability inventory: The skill utilizes the requests library for HTTP communication. No capabilities for shell command execution, file system modification, or persistence were found.
Sanitization: The skill does not perform sanitization on the retrieved document content, passing the raw text directly to the agent.

byted-viking-aisearch-feishu