hiring-signal-outreach

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. It ingests untrusted data from job descriptions and uses it to influence the content of generated outreach emails. * Ingestion points: External job postings from LinkedIn, Indeed, and Apollo (SKILL.md). * Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing the fetched job description text (SKILL.md). * Capability inventory: The skill uses web-search, job-search, contact-finding, and email-drafting capabilities (SKILL.md). * Sanitization: There is no evidence of content sanitization or validation for the data retrieved from external sources before it is used in prompts (SKILL.md).
  • [EXTERNAL_DOWNLOADS]: The skill interacts with various well-known external platforms and APIs, such as Apollo, LinkedIn, and outreach tools like Smartlead and Instantly, to perform data enrichment and campaign execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:03 PM