seo-backlinks

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from web pages and API responses, creating a potential surface for indirect prompt injection. * Ingestion points: Web pages fetched by verify_backlinks.py and JSON responses from Moz, Bing, and DataForSEO APIs are ingested into the agent's context. * Boundary markers: The skill contains a dedicated 'Security' section with explicit instructions to the agent to treat fetched content as data only and to ignore any instructions or commands found within it. * Capability inventory: The skill executes various scripts (moz_api.py, backlinks_auth.py, etc.) via shell commands, which could be targets for manipulation if injection occurs. * Sanitization: While instructions exist to ignore embedded commands, there is no technical sanitization or structural delimiting of the external content described in the prompt logic.
  • [COMMAND_EXECUTION]: The skill relies on executing local Python scripts to perform its analysis, which is the intended behavior for this toolset. * The scripts are located in ${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo and include tools such as moz_api.py, bing_webmaster.py, and commoncrawl_graph.py.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 02:01 PM