ads-linkedin

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill's primary function is to process external LinkedIn Ads data and Campaign Manager exports, which presents an attack surface for indirect prompt injection.
  • Ingestion points: The 'Process' section in SKILL.md specifies collecting LinkedIn Ads data and Campaign Manager exports.
  • Boundary markers: There are no specified delimiters or instructions to ignore embedded prompts within the external data.
  • Capability inventory: The skill performs read-only operations on local reference files (e.g., ads/references/linkedin-audit.md) and logical data evaluation; it does not exhibit dangerous capabilities like code execution or network exfiltration.
  • Sanitization: No sanitization or validation of the ingested CSV or export data is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 10:42 AM
Security Audit — agent-trust-hub — ads-linkedin