gr-backlinks

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The scripts/backlinks-audit.py script makes network requests to external services to fulfill its auditing functions. It retrieves data from the Common Crawl index (index.commoncrawl.org) and the DataForSEO API (api.dataforseo.com), using the DATAFORSEO_B64 environment variable for secure authentication. Additionally, the script includes a verification crawler that attempts to access arbitrary URLs provided by the user to confirm the presence of specific backlinks.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface due to its handling of data from external, untrusted sources.
  • Ingestion points: The verify_known_link function in scripts/backlinks-audit.py fetches and reads up to 500,000 characters of content from external webpages.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potential commands embedded within the fetched webpage content.
  • Capability inventory: The script can perform network requests and write results to the console, which are then integrated into the agent's context. The skill also allows for file writes to data/backlinks.jsonl.
  • Sanitization: No sanitization, validation, or filtering of the external webpage content is performed before the script searches for the target domain string.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 09:21 AM
Security Audit — agent-trust-hub — gr-backlinks