content-parse

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill performs network requests to doubaoya.com to fetch metadata from user-provided URLs. This is the core function of the skill and the domain is associated with the vendor's documented service.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to the ingestion and processing of untrusted data from external sources.
  • Ingestion points: Data retrieved from external URLs via the doubaoya.com API is presented to the agent context through the output of scripts/parse_content.py.
  • Boundary markers: The skill's instructions lack explicit delimiters (like XML tags or custom markers) or specific 'ignore' instructions for the agent to bypass commands embedded in the external content.
  • Capability inventory: The agent environment allows for the execution of shell commands and scripts, which increases the potential impact of successful injection.
  • Sanitization: The skill does not filter or sanitize the content returned by the API (e.g., video titles or author names) before it is passed to the agent for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 07:49 PM
Security Audit — agent-trust-hub — content-parse