slack-bot
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill contains a workflow for sharing blog posts where it fetches metadata (title, description, author) from external URLs using WebFetch. This untrusted content is then interpolated into Slack message templates. While this presents an indirect prompt injection surface, the skill mitigates this by instructing the agent to show the full payload to the user and request explicit confirmation before sending.
- [COMMAND_EXECUTION]: The skill makes extensive use of the Bash tool to execute curl commands for Slack API interactions. It also uses python3 -c for parsing API responses, calculating timestamps, and listing channels.
- [DYNAMIC_EXECUTION]: The instructions provide templates for dynamically building JSON payloads by concatenating shell variables within a python3 -c command. This technique is used to ensure proper JSON formatting but involves runtime assembly of executable logic.
Audit Metadata