guest-blogger

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by scanning local project files, creating an attack surface where malicious instructions embedded in documents could influence the agent's behavior.
  • Ingestion points: The agent uses Glob and Read tools to scan files in directories like blog/, posts/, and product/service pages (SKILL.md, Step 1).
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the files being analyzed.
  • Capability inventory: The skill uses file-reading tools and generates structured reports and email templates based on the analyzed content.
  • Sanitization: There is no mention of sanitizing, filtering, or escaping the content extracted from the local project files before it is used for report generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:33 PM