competitive-intel

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because it is designed to ingest and analyze untrusted data from external sources.
  • Ingestion points: The Research phase (Phase 2) explicitly directs the agent to gather data from 'G2/Capterra reviews,' 'social media and community discussions,' and 'competitor blog posts' in SKILL.md.
  • Boundary markers: There are no specific boundary markers or 'ignore embedded instructions' warnings defined in the prompt templates to isolate this external content from the agent's internal logic.
  • Capability inventory: The skill includes execution of a local Python script ('scripts/check-output.py') and involves file reading and asset generation.
  • Sanitization: No sanitization, filtering, or validation steps are mentioned for the external content before it is processed and summarized by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 03:21 PM
Security Audit — agent-trust-hub — competitive-intel