competitive-ads-extractor

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill is designed to ingest and analyze untrusted data from external sources.
  • Ingestion points: Ad headlines, descriptions, and copy scraped from Facebook and LinkedIn (SKILL.md).
  • Boundary markers: Absent. There are no instructions to use delimiters or ignore embedded commands in the source text.
  • Capability inventory: The skill describes capabilities for network access (scraping) and file system modification (writing reports to ~/competitor-ads/).
  • Sanitization: None. The skill does not mention filtering or escaping the ingested content.
  • Data Exposure & Exfiltration (LOW): The skill's workflow involves writing captured data and analysis to the user's local filesystem (e.g., ~/competitor-ads/). While standard for this use case, users should be aware of the agent's file system access level.
  • No Code (INFO): No executable scripts, binaries, or dependency manifests were provided for analysis. The evaluation is based on the behavioral instructions and examples within the markdown documentation.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 12:17 AM