icp-score-and-route

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied lead lists and scoring criteria from the $ARGUMENTS variable.
  • Ingestion points: Lead names, domains, and ICP criteria input via $ARGUMENTS in SKILL.md.
  • Boundary markers: None present; the skill does not explicitly instruct the agent to ignore instructions embedded within the lead data.
  • Capability inventory: The skill has no dangerous capabilities; it lacks access to shell commands, file system writes, or arbitrary network execution.
  • Sanitization: No explicit input sanitization is mentioned, but the absence of powerful tools makes the risk negligible.
  • [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill references a workflow from Lusha's official 'Campus' library. As Lusha is a well-known professional service for sales intelligence, this reference is legitimate and safe.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 02:35 PM
Security Audit — agent-trust-hub — icp-score-and-route