competitive-strategy-tracker

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and processes untrusted data from the web to perform analysis and generate recommendations.\n
  • Ingestion points: The skill actively scans external competitor websites, blog posts, social media platforms (LinkedIn, Twitter, YouTube), and third-party review sites such as G2 and Capterra to collect competitive intelligence.\n
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between internal instructions and untrusted data fetched from external sources.\n
  • Capability inventory: The skill possesses capabilities for web searching and writing to local files within the profile_directory to maintain historical profiles and timelines.\n
  • Sanitization: No validation, escaping, or sanitization techniques are described for the content retrieved from external sources before it is interpreted by the agent for strategic analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:06 PM
Security Audit — agent-trust-hub — competitive-strategy-tracker