campaign-strategy

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze content from untrusted external websites as part of its core research protocol.\n
  • Ingestion points: The 'Systematic Page Crawling' and 'Homepage Analysis' steps in SKILL.md instruct the agent to fetch and extract data from various pages of a client or prospect website, including case studies and blog posts.\n
  • Boundary markers: The instructions lack specific delimiters or directions to ignore instructions that might be embedded within the content of the crawled websites.\n
  • Capability inventory: The skill uses the extracted data to generate detailed campaign strategies, which are saved to local markdown files (profiles//campaign-strategy.md), and to formulate queries for external data enrichment tools.\n
  • Sanitization: There is no evidence of input validation or content filtering for the data retrieved during the web crawling process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:01 AM