byted-link-reader
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external websites, PDFs, and videos, which creates an attack surface for indirect prompt injection attacks where malicious data could override agent behavior.\n
- Ingestion points: The link_reader function in scripts/link_reader.py fetches and processes content from external URLs provided at runtime.\n
- Boundary markers: The skill does not implement specific delimiters or instructions to ignore commands that may be embedded in the fetched content.\n
- Capability inventory: The skill performs network operations to ByteDance's Ark API and instructions are provided for the agent to write to environment files in the local workspace.\n
- Sanitization: There is no evidence of sanitization or filtering of the retrieved content to remove potential injection patterns before the data is returned to the agent.
Audit Metadata