share-of-voice

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts competitor-tracker.py and geo-tracker.py to persist share-of-voice data and perform GEO audits.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves data from well-known services including Google Ads, Meta Ads, and Brandwatch using Model Context Protocols (MCP).
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests and processes untrusted data from social media mentions and AI-generated search results.
  • Ingestion points: Social mentions retrieved via the Brandwatch MCP and AI-generated responses collected during GEO auditing in step 5.
  • Boundary markers: The skill does not implement boundary markers or instructions to ignore embedded commands within the processed data.
  • Capability inventory: The skill maintains the ability to execute subprocesses (competitor-tracker.py, geo-tracker.py) and perform file system operations within the ~/.claude-marketing/ directory.
  • Sanitization: There is no evidence of sanitization, filtering, or escaping of the external social content or AI responses before they are analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 01:03 PM