competitive-intel

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it is designed to ingest and process data from external, untrusted sources such as competitor websites and third-party review platforms.
  • Ingestion points: The multi-agent research tasks in SKILL.md fetch content from external sites like G2, Capterra, and competitor blogs.
  • Boundary markers: There are no explicit markers or instructions to isolate or ignore potential malicious instructions embedded in the external content.
  • Capability inventory: The skill is limited to delegating research tasks to sub-agents and does not possess capabilities for file-system modification or shell command execution.
  • Sanitization: No sanitization or validation of the ingested external data is performed prior to its use in generating battlecards and positioning maps.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:06 PM
Security Audit — agent-trust-hub — competitive-intel