competitor-research-playbook

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill provides structured documentation, comparison tables, and search templates for performing competitive research. It mentions well-known services such as Wayback Machine, SimilarWeb, and Semrush.
  • [NO_CODE]: There are no executable scripts (Python, JavaScript, Shell), binaries, or automated tool definitions included in the skill.
  • [INDIRECT_PROMPT_INJECTION]: The research methodology involves analyzing data from external social media platforms and web archives. Evidence chain: 1. Ingestion points: Historical website snapshots (Wayback Machine) and social media content (X/Twitter) as described in Sections 1.2 and 3 of SKILL.md. 2. Boundary markers: None present in the instructional text. 3. Capability inventory: No automated tools or code execution capabilities are requested or defined. 4. Sanitization: Not applicable to this documentation-only skill. This ingestion surface is typical for research tasks and does not elevate the security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 07:11 AM
Security Audit — agent-trust-hub — competitor-research-playbook