facebook-research

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill transmits a user-provided API key (CRAWLORA_API_KEY) to the vendor's API endpoint (api.crawlora.net) to authenticate requests. This is standard functionality for an API-integrated skill.
  • [PROMPT_INJECTION]: The skill processes data from external Facebook listings and public Pages, which serves as a potential surface for indirect prompt injection.
  • Ingestion points: Data is received from the /facebook/marketplace/search and /facebook/{page} API endpoints.
  • Boundary markers: None identified in the instructions to separate external data from system prompts.
  • Capability inventory: The skill uses a bash script (scripts/crawlora.sh) to execute curl commands for data retrieval.
  • Sanitization: No explicit sanitization or filtering of the retrieved JSON data is performed within the provided scripts before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 06:52 PM
Security Audit — agent-trust-hub — facebook-research