NYC

market-intelligence-gather

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill's primary function is to ingest untrusted data from external ad libraries and process it with an LLM, which presents a surface for indirect prompt injection attacks. \n
  • Ingestion points: Untrusted content is scraped from external websites including Facebook Ad Library, LinkedIn, and other unspecified ad platforms. \n
  • Boundary markers: Absent. The skill documentation does not provide instructions for the agent to use delimiters or ignore embedded instructions within the scraped ad copy. \n
  • Capability inventory: The agent performs network requests (scraping), writes to the local filesystem (~/competitor-ads/), and performs natural language analysis on the scraped data. \n
  • Sanitization: Absent. There is no mention of validating, filtering, or escaping the external content before it is processed by the AI. \n- No Code (SAFE): The provided file is a pure Markdown document containing instructions and metadata. It does not include any Python scripts, Node.js packages, or binary executables that could perform malicious actions independently.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:33 PM