pm-competitor-deconstructor

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists exclusively of markdown documentation and instructional prompts designed to guide an AI agent through a product analysis workflow. It does not contain any executable scripts, binary files, or automated commands.
  • [SAFE]: No hardcoded credentials, sensitive file path access, or data exfiltration patterns were detected. The skill naturally requests context about the user's product to tailor the analysis, which is standard functional behavior for this use case.
  • [EXTERNAL_DOWNLOADS]: The file references/data-sources.md identifies several well-known and reputable industry services (such as SimilarWeb, Crunchbase, Product Hunt, and G2) as recommended sources for information gathering. These are presented as manual research suggestions for the analyst and do not involve automated or suspicious download patterns.
  • [PROMPT_INJECTION]: No evidence of malicious prompt injection, behavior overrides, or safety bypass instructions were found in the skill or its reference files.
  • [NO_CODE]: The skill is entirely text-based and does not leverage any programming languages or runtime environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 06:31 AM