funding-event-prospector

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.
  • Ingestion points: Step 3 (WebFetch) reads content from external websites (e.g., TechCrunch, Crunchbase) to extract funding details.
  • Boundary markers: The skill does not define explicit boundary markers or instructions for the agent to ignore potential commands embedded within the retrieved web content.
  • Capability inventory: The skill utilizes mcp__claude_ai_Amplemarket__enrich_person (which consumes credits and reveals contact details) and mcp__claude_ai_Amplemarket__create_lead_list (which writes data to the vendor's service).
  • Sanitization: There is no evidence of sanitization or filtering of the fetched content before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves data from well-known news services (TechCrunch, Crunchbase) to identify funding events, which is consistent with its stated purpose.
  • [DATA_EXFILTRATION]: No unauthorized data exfiltration was detected. Data enrichment and lead list creation are performed through the author's own infrastructure (Amplemarket MCP server).
  • [CREDENTIALS_UNSAFE]: No hardcoded credentials or unsafe handling of secrets were found. The skill leverages standard MCP tool authentication.
  • [COMMAND_EXECUTION]: The skill does not execute shell commands, perform privilege escalation, or establish persistence.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 11:36 PM
Security Audit — agent-trust-hub — funding-event-prospector