ai-cold-outreach
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to help users build automation pipelines that ingest untrusted external data (such as LinkedIn social posts, job postings, and news articles) to generate personalized outreach. This creates a surface for indirect prompt injection if the external data contains instructions designed to manipulate the LLM's output.
- Ingestion points: Enriched lead data including social media content, company news, and hiring signals (SKILL.md).
- Boundary markers: The provided prompt templates do not include explicit delimiters or instructions to ignore potential commands embedded within the external data.
- Capability inventory: The resulting systems are designed to perform network operations, specifically sending automated emails to third parties.
- Sanitization: The skill lacks guidance on validating, filtering, or escaping external content before it is interpolated into LLM prompts.
Audit Metadata