facebook-posts
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill communicates with the vendor's API at https://redfox.hk/story/api/fb/userPosts to retrieve Facebook post data.\n- [COMMAND_EXECUTION]: The skill executes a Python script (scripts/fetch_posts.py) to handle URL processing, API requests, and local data storage.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external content from Facebook posts, which represents a potential attack surface for indirect prompt injection.\n
- Ingestion points: External post data is fetched from Facebook via the RedFox API and processed within scripts/fetch_posts.py.\n
- Boundary markers: The agent is instructed to format the output into Markdown tables, providing a structural delimiter for the untrusted content.\n
- Capability inventory: The script has the capability to write JSON files to the local output/ directory.\n
- Sanitization: The script performs basic text normalization and truncation on post captions, though it does not explicitly filter for potential prompt injection patterns in the retrieved data.
Audit Metadata