sales-intelligence

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external platforms (LinkedIn, Twitter, Google News) which are outside the agent's direct control.
  • Ingestion points: Data is retrieved using the tools listed in SKILL.md, including linkedin_web_v2_user_profile and twitter_web_search_timeline.
  • Boundary markers: No specific delimiters are defined in the instructions to isolate external data from the prompt.
  • Capability inventory: There are no dangerous local capabilities defined in this skill, such as file system modifications or shell command execution.
  • Sanitization: The instructions do not specify any filtering or sanitization of external content.
  • [NO_CODE]: This skill contains no executable scripts or binaries; it consists solely of markdown instructions and documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 11:31 PM
Security Audit — agent-trust-hub — sales-intelligence