early-access-email-sequence

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted external data.
  • Ingestion points: The skill uses WebSearch and WebFetch in Phases 1 and 2 (defined in SKILL.md) to retrieve content from LinkedIn-related search results and company websites.
  • Boundary markers: The instructions do not define clear delimiters or use system-level warnings to separate the retrieved web content from the agent's core instructions, making it possible for malicious text on a processed website to hijack the agent's context.
  • Capability inventory: The skill possesses significant capabilities, including writing to external Notion databases (notion-create-pages, notion-create-database) and performing further web operations, which could be abused if an injection is successful.
  • Sanitization: There is no evidence of content filtering, escaping, or validation of the data fetched from the web before it is interpolated into email generation templates or database properties.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:17 PM