linkedin-ads-ctr-signal

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external data from LinkedIn Ads creatives, such as headlines and intro text, to inform outreach angles. This data is passed to a sub-agent without explicit sanitization, presenting an indirect prompt injection surface.
  • Ingestion points: Creative-level analytics and metadata (Step 3) and workspace company records (Step 5).
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands within the ingested ad content.
  • Capability inventory: The sub-agent performs company research, generates outreach drafts, and updates company memory with processing timestamps (Steps 5 and 6).
  • Sanitization: No validation, escaping, or filtering of the external LinkedIn content is specified before it is used to contextualize the agent's drafting task.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 04:39 PM
Security Audit — agent-trust-hub — linkedin-ads-ctr-signal