competitor-profiling

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill performs its stated purpose of competitor profiling using established tools (Firecrawl and DataForSEO) for market research.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external URLs via firecrawl_scrape (in SKILL.md). This represents a potential vulnerability surface where a competitor's website could contain hidden instructions for the AI. However, the skill explicitly mitigates this risk in the 'Input não confiável' section by instructing the agent to ignore embedded instructions and report such attempts.
  • [COMMAND_EXECUTION]: The skill performs file system operations, specifically writing markdown and JSON files to a local competitor-profiles/ directory. These actions are limited to the skill's intended scope for data storage and report generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 10:24 PM