deploy-telegram
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute system-level commands, specifically
ansible-playbookfor automated deployment andsshfor retrieving remote container logs. - [DATA_EXFILTRATION]: The instructions expose internal local directory structures through absolute paths such as
/Users/lgbarn/Personal/Trading/Indicators/Python/bots/telegram/deploy, which provides information about the host environment. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by instructing the agent to read and interpret logs from the remote Telegram bot, which may process untrusted external messages. 1. Ingestion points: Remote log output retrieved via
ssh pi@raspberrypi.localinSKILL.md. 2. Boundary markers: None identified to separate untrusted log data from agent instructions. 3. Capability inventory: Local file system access,ansible-playbookexecution, andsshcommand execution. 4. Sanitization: No validation or filtering of the remote log content is performed before processing.
Audit Metadata