narrative-landscape

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its processing of untrusted data from external websites.\n
  • Ingestion points: Competitor messaging sources (URLs) specified in the 'Input Required' section and processed in 'Analyze each competitor's positioning'.\n
  • Boundary markers: Absent. The instructions do not define delimiters or warnings to ignore instructions within the retrieved content.\n
  • Capability inventory: The skill uses the 'competitor-intelligence' and 'marketing-strategist' agents and executes the 'narrative-mapper.py' script.\n
  • Sanitization: Absent. The skill does not indicate any sanitization or validation of content fetched from external URLs.\n- [COMMAND_EXECUTION]: The skill executes a local Python script 'narrative-mapper.py' to process competitor data and generate the landscape map.\n- [EXTERNAL_DOWNLOADS]: The skill performs network requests to retrieve data from user-provided URLs for competitive analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 01:18 AM