news-signal-outreach

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to its core functionality of ingesting external, untrusted content to drive downstream agent actions.
  • Ingestion points: Step 1 (Parse & Extract) fetches content from user-provided URLs (LinkedIn posts, news articles) or results from automated web searches.
  • Boundary markers: Absent. The instructions do not define specific delimiters or instructions for the agent to treat fetched content as data rather than instructions.
  • Capability inventory: The skill utilizes web-search, contact discovery tools (Apollo, LinkedIn, Clearbit), and outreach management platforms (Smartlead, Outreach.io).
  • Sanitization: Absent. There is no evidence of sanitization or escaping of external content before it is processed by the LLM to identify connection angles or draft outreach emails.
  • [NO_CODE]: The skill consists entirely of markdown instructions and YAML configuration, with no executable scripts or binary files included.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 10:48 AM