kill-or-keep
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from sources including campaign export files, sender exports, and variant result files (SKILL.md, Step 5).
- Ingestion points: Reads external files provided by the user for campaign, sender, and variant data.
- Boundary markers: None explicitly defined to separate untrusted data from instructions.
- Capability inventory: Executes
clayCLI commands for data retrieval and one state-changing action (clay campaigns variants end-test) at Step 8; writes report files to the working directory. - Sanitization: Implements basic validation for numeric values, date formats, and column existence.
- [COMMAND_EXECUTION]: The skill uses the
clayCLI to interact with the Clay platform for listing campaigns, fetching analytics, and ending variant tests (SKILL.md, Steps 0, 1, 3, 5, 8). These commands are essential to the skill's primary purpose and target the vendor's own infrastructure.
Audit Metadata