verify-this
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8). It ingests claims and evidence from the local environment (ingestion points: code, PRs, logs) without explicit boundary markers or sanitization to prevent data from being interpreted as instructions. The workflow involves significant capabilities (capability inventory: control-cli, repro scripts) that could be misused if the input is poisoned.\n- [COMMAND_EXECUTION]: The skill workflow necessitates the execution of platform tools (control-cli, control-ui) and dynamically generated scripts. This is the intended behavior for claim verification but represents a capability that could be leveraged for command injection if the underlying claim or data is malicious.
Audit Metadata