competitive-ads-extractor

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown documentation and instructions with no accompanying Python, Node.js, or other executable scripts.
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection as it ingests untrusted data from third-party ad libraries.
  • Ingestion points: Scraped ad copy and metadata from Facebook Ad Library and LinkedIn.
  • Boundary markers: Absent; the skill does not provide delimiters or instructions to ignore commands embedded within the scraped content.
  • Capability inventory: The agent is expected to scrape web content, capture screenshots, and write files to the local file system.
  • Sanitization: Absent; there is no logic described for sanitizing or validating the ingested ad content before it is analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 03:12 PM