article-extractor
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the Bash tool to run specific local scripts including
mql5_extract.pyandscripts/official_docs_extractor.pyfor its core functionality.\n- [EXTERNAL_DOWNLOADS]: The skill usescurlto fetch content frommql5.com. Although this is limited to the specific target domain, it involves interaction with an external network resource not on the primary whitelist.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) due to the ingestion of external web data.\n - Ingestion points: Articles and documentation are downloaded from
mql5.comand processed into the agent's workspace.\n - Boundary markers: There are no specified delimiters or 'ignore' instructions provided to the agent to prevent it from following commands potentially embedded in the scraped HTML or Markdown.\n
- Capability inventory: The agent has access to
Bash,Grep, andGlobtools, which could be exploited if malicious instructions are present in the extracted articles.\n - Sanitization: The skill documentation does not describe any sanitization or validation of the article text before it is presented to or used by the agent.
Audit Metadata