sequence-load

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection Surface]: The skill ingests untrusted data which could potentially influence agent behavior.\n
  • Ingestion points: Search criteria and sequence names are parsed from the $ARGUMENTS variable in SKILL.md (Step 1).\n
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the user-provided input in SKILL.md.\n
  • Capability inventory: The skill possesses capabilities for lead search, contact enrichment, and email campaign enrollment via the Apollo MCP tools in SKILL.md.\n
  • Sanitization: The instructions in SKILL.md do not include specific validation or sanitization steps for the input data before it is passed to search tools.\n- [Data Access and Credit Usage]: The skill performs actions that retrieve contact data and consume platform credits.\n
  • Evidence: Step 5 utilizes the bulk match tool with personal email revealing enabled.\n
  • Consideration: This functionality is central to the skill's purpose but involves sensitive information and credit consumption. The skill mitigates risk by requiring user approval in Step 4 before these steps occur.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:27 PM
Security Audit — agent-trust-hub — sequence-load