news-signal-outreach

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Risk. The skill is designed to fetch and analyze content from external URLs (news articles, LinkedIn posts, tweets) to qualify leads and draft personalized outreach.
  • Ingestion points: The skill explicitly ingests data from external URLs and raw text provided in the news_input object in SKILL.md (Step 1).
  • Boundary markers: There are no specific instructions or delimiters defined to isolate the fetched news content from the agent's instructions, nor are there 'ignore embedded instructions' warnings.
  • Capability inventory: The skill utilizes web-search, contact-finding, and email-drafting capabilities, which are used to generate content that may be sent to third parties.
  • Sanitization: No sanitization or validation logic is specified for the external content before it is processed by the LLM for reasoning and drafting.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:03 PM