sales-sequences
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a local Python script located at
scripts/sequence_days.pyto calculate sequence schedules and perform mechanical checks on email drafts (such as word counts and character validation). The script is self-contained, uses only the Python standard library, and performs no network or sensitive file system operations. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data, including fetched web pages, uploaded files, and pasted CRM notes. It incorporates high-priority security instructions that explicitly direct the agent to treat all such external content as data rather than instructions, and to report any detected attempts to override agent behavior.
- [EXTERNAL_DOWNLOADS]: The skill permits the agent to fetch web pages to verify product claims or proof points as requested by the user. These operations are scoped to user-provided URLs and are subject to the skill's anti-injection protocols.
Audit Metadata