Competitor Tracker

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill outlines workflows (Workflow 2) for monitoring competitor websites, social media, and customer reviews, which involves processing untrusted external content. 1. Ingestion points: SKILL.md (Workflow 2). 2. Boundary markers: No delimiters or ignore-instructions are specified in the markdown. 3. Capability inventory: No custom scripts or tools are included; the skill relies on the agent's core capabilities. 4. Sanitization: No input validation or sanitization instructions are provided.
  • [NO_CODE] (SAFE): This skill contains no Python, Node.js, or shell scripts, eliminating the possibility of direct remote code execution or persistence via the skill itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:17 PM