narrative-landscape

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from external sources such as competitor websites, advertising copy, and social media profiles to identify positioning signals.
  • Ingestion points: Competitor messaging sources extracted in Step 3 of the process.
  • Boundary markers: No boundary markers or 'ignore' instructions are used to separate untrusted data from the agent's internal logic.
  • Capability inventory: The skill executes a local script (narrative-mapper.py) to process the positioning data.
  • Sanitization: No evidence of sanitization or escaping of the external content is present.
  • [COMMAND_EXECUTION]: The skill executes a local Python script narrative-mapper.py with the command 'map-landscape'. This script processes data that includes values derived from external competitor messaging, which could lead to unexpected behavior if the script does not properly handle malicious inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 01:02 PM