data-scraper-agent
Fail
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: CRITICALINDIRECT_PROMPT_INJECTIONPRIVILEGE_ESCALATIONCOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external web sources like HTML, JSON, RSS feeds, and PDF documents using
requests,playwright, andBeautifulSoupas seen inSKILL.mdandpayloads.md. This creates an attack surface for indirect prompt injection where malicious instructions in external content could influence the agent. The skill lacks explicit boundary markers or sanitization logic. Capabilities include file system writes, network requests, and subprocess execution. - [PRIVILEGE_ESCALATION]: The
payloads.mdfile contains a command to manage the Tor service which requires elevated permissions:sudo systemctl start tor. - [COMMAND_EXECUTION]: The skill interacts with the
searchsploitCLI tool using Python'ssubprocessmodule and demonstrates the use ofparallelfor batch processing shell commands inpayloads.mdand the rate-limiting guide. - [DATA_EXFILTRATION]: Documentation in
payloads.mdprovides patterns for searching and extracting sensitive credentials like API keys and private keys from GitHub repositories using theghCLI tool. - [EXTERNAL_DOWNLOADS]: The skill fetches vulnerability and advisory data from external platforms including
services.nvd.nist.gov,cveawg.mitre.org, andapi.github.com. It also provides examples for enumerating hidden service directories on the Tor network inpayloads.md.
Recommendations
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata